added accuracy improvement logic

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+*pyc
+# C extensions
+#*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+.idea/
\ No newline at end of file

.gitlab-ci.yml

+stages:
+  - auto-tagging
+  - build
+  - deploy
+  - update
+  
+variables:
+  MYSQL_CONNECTION: "mysql -h $MYSQL_HOST -u $MYSQL_USER -p$MYSQL_PASS "
+  # STATUS_SCRIPT: /home/gitlab-runner/monitor/deployment-status.sh
+  # HELM_CHART: /home/gitlab-runner/kubernetes/ilens/$QA_ENV/ilens-modules
+  # VARIABLES_YML: variables.yml
+  # DEPLOYMENT_YML: metadata-services.yml
+  TIMEOUT: 960s
+
+before_script:
+  - val=`echo $($MYSQL_CONNECTION -e "SELECT COUNT(*) FROM $VERSION_DB.$DB_TABLE WHERE category='customer-implementations' AND type='AI' AND os='docker' AND module_name='$CI_PROJECT_NAME' ") | cut -d " " -f2`
+  - if [ $val == 0 ]; then $MYSQL_CONNECTION -e "INSERT INTO $VERSION_DB.$DB_TABLE values('customer-implementations','AI','$CI_PROJECT_NAME','docker', '0', '0', '0', '0')";fi
+  - QA=$($MYSQL_CONNECTION -N -e "SELECT qa FROM $VERSION_DB.$DB_TABLE where module_name = '$CI_PROJECT_NAME' AND type = 'AI' AND category = 'customer-implementations' AND os = 'docker'")
+  - DEV=$($MYSQL_CONNECTION -N -e "SELECT dev FROM $VERSION_DB.$DB_TABLE where module_name = '$CI_PROJECT_NAME' AND type = 'AI' AND category = 'customer-implementations' AND os = 'docker'")
+  - UAT=$(mysql -h $MYSQL_HOST -u $MYSQL_USER -p$MYSQL_PASS -N -e "SELECT uat FROM $VERSION_DB.$DB_TABLE where module_name = '$CI_PROJECT_NAME' AND type = 'AI' AND category = 'customer-implementations' AND os = 'docker'")
+  - PROD=$($MYSQL_CONNECTION -N -e "SELECT prod FROM $VERSION_DB.$DB_TABLE where module_name = '$CI_PROJECT_NAME' AND type = 'AI' AND category = 'customer-implementations' AND os = 'docker'")
+
+auto-tagging:
+  stage: auto-tagging
+  before_script:
+    - val=`echo $($MYSQL_CONNECTION -e "SELECT COUNT(*) FROM $VERSION_DB.$VERSION_RELEASE_TABLE WHERE  module_name='$CI_PROJECT_NAME' ") | cut -d " " -f2`
+    - if [ $val == 0 ]; then $MYSQL_CONNECTION -N -e "INSERT INTO $VERSION_DB.$VERSION_RELEASE_TABLE values('$CI_PROJECT_NAME', 'iLens', '0', '0', '0', '0')";fi
+    - ILENS=$($MYSQL_CONNECTION -N -e "SELECT ilens_version FROM "$VERSION_DB.$VERSION_RELEASE_TABLE" where module_name = '$CI_PROJECT_NAME'")
+    - RELEASE=$($MYSQL_CONNECTION -N -e "SELECT release_version FROM "$VERSION_DB.$VERSION_RELEASE_TABLE" where module_name = '$CI_PROJECT_NAME'")
+    - FEATURE=$($MYSQL_CONNECTION -N -e "SELECT feature_version FROM "$VERSION_DB.$VERSION_RELEASE_TABLE" where module_name = '$CI_PROJECT_NAME'")
+    - PATCH=$($MYSQL_CONNECTION -N -e "SELECT patch_version FROM "$VERSION_DB.$VERSION_RELEASE_TABLE" where module_name = '$CI_PROJECT_NAME'")
+
+  script:
+    - SOURCE_BRANCH=$(echo $CI_COMMIT_TITLE | cut -f 3 -d " " | cut -f 1 -d "/" | cut -f 2 -d "'")
+    - >
+        if [ "$SOURCE_BRANCH" = "QA" ]; then
+          ((RELEASE=RELEASE+1)) && FEATURE=0 && PATCH=0;
+          TAG_NAME=v$RELEASE.$FEATURE
+          IMAGE_URL=azracrilensai.azurecr.io/repository/ilens-ai/customer-implementations/acc/$CI_PROJECT_NAME:"$TAG_NAME"
+          PROD=$RELEASE; QA=0; DEV=0;
+          $MYSQL_CONNECTION -e "UPDATE $VERSION_DB.$DB_TABLE SET prod='$PROD' ,qa='$QA', dev='$DEV' WHERE module_name='$CI_PROJECT_NAME' AND type='AI' AND category='customer-implementations' AND os='docker'"         
+        elif [ $SOURCE_BRANCH == "feature" ]; then
+          ((FEATURE=FEATURE+1)) && PATCH=0;
+          TAG_NAME=v$RELEASE.$FEATURE
+          IMAGE_URL=azracrilensai.azurecr.io/repository/ilens-ai/customer-implementations/acc/$CI_PROJECT_NAME:"$TAG_NAME"
+        elif [ $SOURCE_BRANCH == "patch" ]; then
+          ((PATCH=PATCH+1));
+          TAG_NAME=v$RELEASE.$FEATURE.$PATCH
+          IMAGE_URL=azracrilensai.azurecr.io/repository/ilens-ai/customer-implementations/acc/$CI_PROJECT_NAME:"$TAG_NAME"
+        else
+          exit 1
+        fi
+        
+    - echo -e "\n\nImage:" $IMAGE_URL >> ReleaseNote.txt
+    - sed -i "1s|^|Version":" $TAG_NAME\n|" ReleaseNote.txt
+    - sed -i "1s|^|Module Name":" $CI_PROJECT_NAME\n|" ReleaseNote.txt
+    - docker build -t $IMAGE_URL .
+    - docker push $IMAGE_URL
+    - docker rmi --force $IMAGE_URL
+    - URL=$(echo $CI_PROJECT_URL | sed 's|https://||')
+    - git remote set-url origin https://$GIT_USRNAME:$GIT_USRPASSWD@$URL
+    - git config user.email "devopsilens@gmail.com"
+    - git config user.name "$GIT_USRNAME"    
+    - git tag -a $TAG_NAME -F ReleaseNote.txt
+    - git push origin $TAG_NAME
+    - $MYSQL_CONNECTION -e "UPDATE $VERSION_DB.$VERSION_RELEASE_TABLE SET release_version='$RELEASE', feature_version='$FEATURE', patch_version='$PATCH'  WHERE module_name = '$CI_PROJECT_NAME' "
+    - $MYSQL_CONNECTION -e "INSERT INTO $HISTORY_DB.$VERSION_RELEASE_TABLE values('$CI_JOB_ID', '$CI_PROJECT_NAME','iLens', '$ILENS.$RELEASE.$FEATURE', '$CI_COMMIT_SHA', '$GITLAB_USER_NAME', '$CI_COMMIT_REF_NAME')"
+  tags:
+    - shell
+  only:
+    - master
+
+#~~~~~| CODE QUALITY |~~~~~#
+codequality:
+  stage: deploy
+  image: azacrknowledgelens.azurecr.io/knowledgelens/klit-operation/devops/gitlab-runner:ubuntu-sonarscanner
+  script:
+     - /opt/sonar-scanner/bin/sonar-scanner -Dsonar.projectKey=$CI_PROJECT_NAME -Dsonar.projectName=$CI_PROJECT_NAME -Dsonar.typescript.node=./node/node -Dsonar.login=admin -Dsonar.password=admin -Dsonar.sources=.
+     - sleep 5
+     - python3 /opt/code_quality_report/static_code_quality_report_csv_v2.py $CI_PROJECT_NAME $GITLAB_USER_EMAIL,$EMAIL_TO $EMAIL_FROM $EMAIL_PASSWD False admin admin
+  only:
+     - develop
+  tags:
+     - docker

app.py

+import os
+from fastapi import FastAPI
+from fastapi import File
+import cv2
+import numpy as np
+import io
+import uvicorn
+from datetime import datetime
+
+ROOT_DIR = os.path.abspath(os.curdir)
+
+
+
+os.environ["config"]="{\"TZ\": \"Asia/Kolkata\", \"MONGO_URI\": \"mongodb://192.168.0.220:2717/admin\", \"MONGO_DATABASE\": \"ilens_ai\", \"MONGO_COLLECTION\": \"janusDeployment\", \"MONGO_KEY\": \"deploymentId\", \"MONGO_VALUE\": \"ACCCementCamera20_61275102\", \"MONGO_COLL\": \"serviceConfiguration\", \"MONGO_DB\": \"ilens_ai\"}"
+from edge_engine.edge_processor import ExecutePipeline
+from edge_engine.edge_processor import Pubs
+from scripts import CementBagCounter
+from edge_engine.common.config import EDGE_CONFIG
+pubs = Pubs()
+mod = CementBagCounter(config=EDGE_CONFIG,
+                       model_config=EDGE_CONFIG["modelConfig"],
+                       pubs=pubs,
+                       device_id=EDGE_CONFIG['deviceId'])
+
+app = FastAPI()
+
+
+
+@app.post("/")
+def extract_text_diectly(file: bytes = File(...)):
+
+    try:
+        stream = io.BytesIO(file)
+        image = np.asarray(bytearray(stream.read()), dtype="uint8")
+        image = cv2.imdecode(image, cv2.IMREAD_COLOR)
+
+
+        file="archive/sample_"+str(datetime.now())+".jpg"
+        file=file.replace(" ","_")
+        file=file.replace("-","_")
+        file = file.replace(":", "_")
+        cv2.imwrite(file, image)
+        ex = ExecutePipeline(mod,image)
+        ex.run_model()
+
+
+        return mod.text_json
+    except Exception as e:
+        print(e)
+
+if __name__ == '__main__':
+    uvicorn.run("app:app", host="localhost", port=8290)
+

app.sh

+source /opt/intel/openvino/bin/setupvars.sh
+python3 app.py
\ No newline at end of file

edge_engine/ai/model/__init__.py

+from edge_engine.ai.model.modelwraper import ModelWrapper

edge_engine/ai/model/modelwraper.py

+from abc import ABC, abstractmethod
+
+
+class ModelWrapper(ABC):
+    def __init__(self, path=None):
+        """Implement code to load mask_model here"""
+        pass
+
+    def _pre_process(self, x):
+        """Implement code to process raw input into format required for mask_model inference here"""
+        return x
+
+    def _post_process(self, x):
+        """Implement any code to post-process mask_model inference response here"""
+        return x
+
+    @abstractmethod
+    def _predict(self, x):
+        """Implement core mask_model inference code here"""
+        pass
+
+    def predict(self, x):
+        pre_x = self._pre_process(x)
+        prediction = self._predict(pre_x)
+        result = self._post_process(prediction)
+        return result

edge_engine/ai/preprocess/__init__.py

+
+
+

edge_engine/ai/preprocess/gammapreprocessor.py

+# import the necessary packages
+import cv2
+import numpy as np
+
+
+class GammaPreprocessor:
+    def __init__(self, gamma=1.0):
+        # creating Gamma table
+        self.invGamma = 1.0 / gamma
+        self.table = np.array([((i / 255.0) ** self.invGamma) * 255
+                          for i in np.arange(0, 256)]).astype("uint8")
+
+    def preprocess(self, image):
+        return cv2.LUT(image, self.table)

edge_engine/ai/preprocess/imagetoarraypreprocessor.py

+# import the necessary packages
+from keras.preprocessing.image import img_to_array
+
+
+class ImageToArrayPreprocessor:
+    def __init__(self, dataFormat=None):
+        # store the image data format
+        self.dataFormat = dataFormat
+
+    def preprocess(self, image):
+        # apply the Keras utility function that correctly rearranges
+        # the dimensions of the image
+        return img_to_array(image, data_format=self.dataFormat)

edge_engine/ai/preprocess/simplehistogramprocessor.py

+# import the necessary packages
+import cv2
+
+
+class SimpleHistogramPreprocessor:
+    def __init__(self):
+        pass
+
+    def preprocess(self, image):
+        # Run Histogram simple Equalization
+        return cv2.equalizeHist(image)

edge_engine/ai/preprocess/simplepreprocessor.py

+# import the necessary packages
+import cv2
+
+
+class SimplePreprocessor:
+    def __init__(self, width, height, inter=cv2.INTER_AREA):
+        # store the target image width, height, and interpolation
+        # method used when resizing
+        self.width = width
+        self.height = height
+        self.inter = inter
+
+    def preprocess(self, image):
+        # resize the image to a fixed size, ignoring the aspect
+        # ratio
+        return cv2.resize(image, (self.width, self.height),
+                          interpolation=self.inter)

edge_engine/common/config.py

+import os
+import sys
+from edge_engine.common.constants import LicenseModule
+from dateutil import parser
+from datetime import datetime
+from pymongo import MongoClient
+from copy import deepcopy
+import json
+def licence_validator(payload):
+    try:
+        dt = parser.parse(payload['valid_till'])
+        now = datetime.now()
+        if (now > dt):
+            sys.stdout.write("Licence Expired \n".format())
+            sys.stdout.flush()
+            return False
+        return True
+    except KeyError as e:
+        sys.stderr.write("Error loading licence")
+        return False
+
+
+def get_config_from_mongo(mongo_uri, dbname, basecollection,
+                          key, value):
+    mongo = MongoClient(mongo_uri)
+
+    db = mongo[dbname]
+    config = db[basecollection].find_one({key: value}, {"_id": False})
+    return config
+
+
+
+
+def load_conf(config,mongo_uri, dbname):
+    mongo = MongoClient(mongo_uri)
+    db = mongo[dbname]
+    pub_configs = []
+
+    for conf in config['pubConfigs']:
+        if conf["type"].lower() in ["mqtt","mongo",]:
+            key= conf["key"]
+            value=conf["value"]
+            collection = conf["conectionCollection"]
+            pub_conf = db[collection].find_one({key: value}, {"_id": False})
+            pub_conf.update(conf)
+            pub_configs.append(pub_conf)
+        else :
+            pub_configs.append(conf)
+
+    config['pubConfigs'] = pub_configs
+
+    return config
+
+
+
+# """
+# {
+# "MONGO_URI": "mongodb://192.168.3.220:21017",
+# "MONGO_DATABASE": "ilens_thermal_app",
+# "MONGO_COLLECTION": "janus_deployment_details",
+# "MONGO_KEY": "deploymentId",
+# "MONGO_VALUE": "ddd"
+# }
+# """
+
+LOG_LEVEL = os.environ.get("LOG_LEVEL", default="INFO").upper()
+LOG_HANDLER_NAME = os.environ.get("LOG_HANDLER_NAME", default="ilens-edge_engine")
+
+BASE_LOG_PATH = os.environ.get('BASE_LOG_PATH',
+                               default=os.path.join(os.getcwd(), "logs".format()))
+
+if not os.path.isdir(BASE_LOG_PATH):
+    os.mkdir(BASE_LOG_PATH)
+
+CONFIG_ENV  =  json.loads(os.environ.get('config', default=None))
+sys.stdout.write("config->{} \n".format(json.dumps(CONFIG_ENV)))
+MONGO_URI = CONFIG_ENV.get('MONGO_URI', None)
+MONGO_DATABASE = CONFIG_ENV.get('MONGO_DATABASE', None)
+MONGO_COLLECTION = CONFIG_ENV.get('MONGO_COLLECTION', None)
+MONGO_KEY = CONFIG_ENV.get('MONGO_KEY', None)
+MONGO_VALUE = CONFIG_ENV.get('MONGO_VALUE',None)
+
+if MONGO_URI == None \
+        or MONGO_DATABASE is None \
+        or MONGO_COLLECTION is None \
+        or MONGO_KEY is None \
+        or MONGO_VALUE is None:
+    sys.stderr.write("invalid mongo config  \n")
+    sys.exit(1)
+
+EDGE_CONFIG = get_config_from_mongo(
+    mongo_uri=MONGO_URI,
+    dbname=MONGO_DATABASE, basecollection=MONGO_COLLECTION,
+    key=MONGO_KEY, value=MONGO_VALUE
+)
+DEVICE_ID =  EDGE_CONFIG["deviceId"]
+if EDGE_CONFIG is None:
+    sys.stderr.write("invalid EDGE_CONFIG config  \n")
+    sys.exit(1)
+
+EDGE_CONFIG=load_conf(EDGE_CONFIG, mongo_uri=MONGO_URI,
+    dbname=MONGO_DATABASE)
+DATA_PATH = EDGE_CONFIG["inputConf"].get('dataPath',os.path.join(os.getcwd(), "data".format()))
+
+sys.stderr.write("Loading data from {} \n".format(DATA_PATH))
\ No newline at end of file

edge_engine/common/config1.py

+import os
+import sys
+import configparser
+import json
+from scripts.common.constants import LicenseModule
+import base64
+import jwt
+from dateutil import parser
+from datetime import datetime
+import yaml
+from copy import deepcopy
+
+
+def licence_validator(payload):
+    try:
+        dt = parser.parse(payload['valid_till'])
+        now = datetime.now()
+        if (now > dt):
+            sys.stdout.write("Licence Expired \n".format())
+            sys.stdout.flush()
+            return False
+        return True
+    except KeyError as e:
+        sys.stderr.write("Error loading licence")
+        return False
+
+
+CONFIGURATION_FILE = os.environ.get("CONF_PATH", os.path.join(os.getcwd(), "conf{0}settings.conf".format(os.sep)))
+sys.stdout.write("Reading Config from  {} \n".format(CONFIGURATION_FILE))
+sys.stdout.flush()
+__config = configparser.ConfigParser()
+__config.read(CONFIGURATION_FILE)
+
+LOG_LEVEL = os.environ.get("LOG_LEVEL", __config.get('LOGGER', 'loglevel', fallback="DEBUG")).upper()
+LOG_HANDLER_NAME = os.environ.get("LOG_HANDLER_NAME", __config.get('LOGGER', 'loglevel', fallback="face-id"))
+
+BASE_LOG_PATH = os.environ.get('BASE_LOG_PATH',
+                               __config.get('LOGGER', 'basepath', fallback=os.path.join(os.getcwd(), "logs".format())))
+
+if not os.path.isdir(BASE_LOG_PATH):
+    os.mkdir(BASE_LOG_PATH)
+
+DATA_PATH = os.environ.get('BASE_DATA_PATH', __config.get('CLIENT-CONFIG', 'basepath', fallback=os.path.normpath(
+    os.getcwd() + '{}data'.format(os.sep))))
+
+sys.stdout.write("Data base path  {} \n".format(DATA_PATH))
+
+DEVICE_ID = os.environ.get("DEVICE_ID", __config.get('CLIENT-CONFIG', 'deviceid', fallback="<undefined>"))
+
+LICENCE_FILE = os.environ.get("LICENCE_FILE", __config.get('CLIENT-CONFIG', 'licence-life', fallback="license.lic"))
+LICENCE_FILE = os.path.join(DATA_PATH, LICENCE_FILE)
+
+MODEL_CONFIG_FILE = os.environ.get("MODEL_CONFIG_FILE",
+                                   __config.get('CLIENT-CONFIG', 'mask_model=config-path', fallback="mask_model-config.yaml"))
+MODEL_CONFIG_FILE = os.path.join(DATA_PATH, MODEL_CONFIG_FILE)
+
+with open(MODEL_CONFIG_FILE, 'r') as stream:
+    try:
+        MODEL_CONFIG = yaml.safe_load(stream)
+    except yaml.YAMLError as exc:
+        sys.stderr.write(" **Error loading mask_model config ** \n")
+        sys.stderr.flush()
+        #sys.exit(1)
+
+PUBLISHERS = os.environ.get("PUBLISHERS", __config.get('CLIENT-CONFIG', 'publishers', fallback="")).split(",")
+SUBSCRIBER = os.environ.get("SUBSCRIBER", __config.get('CLIENT-CONFIG', 'subscriber', fallback=""))
+if len(PUBLISHERS) == 0:
+    sys.stdout.write("Empty publishers \n")
+CLIENT_ID = os.environ.get("CLIENT_ID", __config.get('CLIENT-CONFIG', 'client-id', fallback="test-client1"))
+
+STREAM_TYPE = os.environ.get("STREAM_TYPE", __config.get('STREAM-CONFIG', 'stream-type', fallback="usbcam"))
+
+MQTT_CONFIG = {"broker": "", "port": "", "topic": "", "clientId": ""}
+MQTT_SUB_CONFIG = deepcopy(MQTT_CONFIG)
+FRAME_WRITE_CONFIG = {"basepath": None, "filenameFormat": "{deviceId}_{frameId}", "format": "jpg"}
+VIDEO_WRITE_CONFIG = {"basepath": None, "format": "mp4"}
+MONGO_WRITE_CONFIG = {"host": None, "port": 27017, "authSource": None, "collection": None, "dbname": None,
+                      "keys": "frameId,deviceId,timestamp,metric"}
+
+PUBLISHER_CONFIGS = []
+for pub in PUBLISHERS:
+    type, Section = pub.split(":")
+    if type == "MQTT":
+        conf = deepcopy(MQTT_CONFIG)
+        conf["broker"] = os.environ.get("{}_broker".format(Section), __config.get(Section, 'broker'))
+        conf["port"] = int(os.environ.get("{}_port".format(Section), __config.get(Section, 'port')))
+        conf["topic"] = os.environ.get("{}_topic".format(Section), __config.get(Section, 'topic'))
+        conf["clientId"] = os.environ.get("{}_clientid".format(Section),
+                                          __config.get(Section, 'clientid', fallback="ghf-test-00"))
+        conf["type"] = type
+        PUBLISHER_CONFIGS.append(conf)
+    elif type == "FRAMEWRITE":
+        conf = deepcopy(FRAME_WRITE_CONFIG)
+        conf["basepath"] = os.environ.get("{}_basepath".format(Section),
+                                          __config.get(Section, 'basepath', fallback=os.path.normpath(
+                                              os.getcwd() + '{sep}out{sep}frames'.format(sep=os.sep))))
+        conf["iformat"] = os.environ.get("{}_iformat".format(Section), __config.get(Section, 'iformat', fallback="jpg"))
+        conf["filenameFormat"] = os.environ.get("{}_file_name_format".format(Section),
+                                                __config.get(Section, 'file_name_format',
+                                                             fallback="{deviceId}_{frameId}"))
+        if not os.path.isdir(conf["basepath"]):
+            sys.stdout.write("Creating {}  \n".format(conf["basepath"]))
+            os.mkdir(conf["basepath"])
+        conf["type"] = type
+        PUBLISHER_CONFIGS.append(conf)
+    elif type == "VIDEOWRITE":
+        conf = deepcopy(VIDEO_WRITE_CONFIG)
+        conf["basepath"] = os.environ.get("{}_basepath".format(Section),
+                                          __config.get(Section, 'basepath', fallback=os.path.normpath(
+                                              os.getcwd() + '{sep}out{sep}videos'.format(sep=os.sep))))
+        # conf["format"] = os.environ.get("{}_format".format(Section),__config.get(Section, 'file_name_format',fallback="mp4"))
+        conf["filenameFormat"] = os.environ.get("{}_file_name_format".format(Section),
+                                                __config.get(Section, 'file_name_format',
+                                                             fallback="{deviceId}_{timestamp}"))
+        conf["fps"] = int(os.environ.get("{}_fps".format(Section),
+                                         __config.get(Section, 'fps',
+                                                      fallback=30)))
+        conf["dims"] = tuple(os.environ.get("{}_dims".format(Section),
+                                            __config.get(Section, 'dims',
+                                                         fallback="620,320")).split(","))
+        if not os.path.isdir(conf["basepath"]):
+            sys.stdout.write("Creating {}  \n".format(conf["basepath"]))
+            os.mkdir(conf["basepath"])
+        conf["type"] = type
+        PUBLISHER_CONFIGS.append(conf)
+    elif type == "MONGO":
+        conf = deepcopy(MONGO_WRITE_CONFIG)
+        conf["host"] = os.environ.get("{}_host".format(Section),
+                                      __config.get(Section, 'host', fallback="localhost"))
+        conf["port"] = int(os.environ.get("{}_port".format(Section),
+                                          __config.get(Section, 'port', fallback="test")))
+        conf["dbname"] = os.environ.get("{}_dbname".format(Section),
+                                        __config.get(Section, 'dbname', fallback="test"))
+        conf["collection"] = os.environ.get("{}_collection".format(Section),
+                                            __config.get(Section, 'collection', fallback="test"))
+        conf["authSource"] = os.environ.get("{}_authsource".format(Section),
+                                            __config.get(Section, 'authsource', fallback=None))
+        conf["username"] = os.environ.get("{}_username".format(Section),
+                                          __config.get(Section, 'username', fallback=None))
+        conf["password"] = os.environ.get("{}_password".format(Section),
+                                          __config.get(Section, 'password', fallback=None))
+        if len(conf["authSource"]) == 0:
+            conf["authSource"] = None
+        conf["keys"] = os.environ.get("{}_keys".format(Section),
+                                      __config.get(Section, 'keys',
+                                                   fallback="frameId,deviceId,timestamp,metric")).split(",")
+        conf["type"] = type
+        PUBLISHER_CONFIGS.append(conf)
+    else:
+        sys.stderr.write("Unsupported  publisher  {} \n".format(type))
+
+if STREAM_TYPE  in ["rtsp", "usbcam"]:
+    FRAME_WIDTH = os.environ.get("FRAME_WIDTH", __config.get('STREAM-CONFIG', 'width', fallback=480))
+    FRAME_HEIGHT = os.environ.get("FRAME_HEIGHT", __config.get('STREAM-CONFIG', 'height', fallback=640))
+    LATENCY = os.environ.get("LATENCY", __config.get('STREAM-CONFIG', 'latency', fallback=0))
+    FRAME_RATE = os.environ.get("FRAME_RATE", __config.get('STREAM-CONFIG', 'framerate', fallback="30/1"))
+    F_FORMAT = os.environ.get("F_FORMAT", __config.get('STREAM-CONFIG', 'fformat', fallback="BGRx"))
+    USE_GSTREAMER = int(os.environ.get("USE_GSTREAMER", __config.get('STREAM-CONFIG', 'use-gstreamer', fallback=1)))
+    CUSTOM_PIPELINE = os.environ.get("CUSTOM_PIPELINE", __config.get('STREAM-CONFIG', 'custom-pipeline', fallback=None))
+    URI = os.environ.get("URI", __config.get('STREAM-CONFIG', 'uri', fallback=0))
+
+    BUILD_CONFIG = {
+        "sourceType": STREAM_TYPE,
+        "width": FRAME_WIDTH,
+        "height": FRAME_HEIGHT,
+        "latency": LATENCY,
+        "framerate": FRAME_RATE,
+        "format": F_FORMAT,
+        "gstreamer": USE_GSTREAMER,
+        "uri": URI
+    }
+
+elif STREAM_TYPE == "mqtt":
+    MQTT_SUB_CONFIG["broker"] = os.environ.get("STREAM-CONFIG_broker", __config.get('STREAM-CONFIG', 'broker'))
+    MQTT_SUB_CONFIG["port"] = os.environ.get("STREAM-CONFIG_port", __config.get('STREAM-CONFIG', 'port'))
+    MQTT_SUB_CONFIG["topic"] = os.environ.get("STREAM-CONFIG_topic", __config.get('STREAM-CONFIG', 'topic'))
+    MQTT_SUB_CONFIG["clientId"] = os.environ.get("STREAM-CONFIG_clientid",
+                                                 __config.get('STREAM-CONFIG', 'clientid', fallback="sdrt"))
+    MQTT_SUB_CONFIG["sourceType"] = STREAM_TYPE
+    BUILD_CONFIG = MQTT_SUB_CONFIG
+elif STREAM_TYPE == "videofile":
+    BUILD_CONFIG = {"uri": os.environ.get("URI", __config.get('STREAM-CONFIG', 'uri', fallback=0)),
+                    "queueSize": os.environ.get("QUEUE_SIZE",
+                                                __config.get('STREAM-CONFIG', 'queue_size', fallback=128)),
+                    "sourceType": STREAM_TYPE}
+else:
+    raise ValueError("unsupported source  {}".format(STREAM_TYPE))
+
+sys.stdout.write("Loading Licence   {} \n".format(LICENCE_FILE))
+try:
+    private_key = LicenseModule.private_key
+    encoding_algorithm = LicenseModule.encoding_algorithm
+    LICENCE_PAYLOAD = jwt.decode(bytes(base64.b64decode(open(LICENCE_FILE, 'rb').read())), private_key,
+                                 algorithms=[encoding_algorithm])
+except Exception as e:
+    sys.stderr.write("{}".format(e))
+    sys.stderr.write(" **Error loading licence** \n")
+    sys.stderr.flush()
+    #sys.exit(1)

edge_engine/common/constants.py

+
+class LicenseModule:
+    private_key = "3139343831323738414d47454e3936363538373136"
+    encoding_algorithm = "HS256"

edge_engine/common/logsetup.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from edge_engine.common.config import LOG_LEVEL, LOG_HANDLER_NAME, BASE_LOG_PATH
+import logging
+from logging.handlers import RotatingFileHandler
+from logging import WARNING,INFO,DEBUG,ERROR
+import os
+
+DEFAULT_FORMAT = '%(asctime)s %(levelname)5s %(name)s %(message)s'
+DEBUG_FORMAT = '%(asctime)s %(levelname)5s %(name)s [%(threadName)5s:%(filename)5s:%(funcName)5s():%(lineno)s] %(message)s'
+
+EXTRA = {}
+
+FORMATTER = DEFAULT_FORMAT
+if LOG_LEVEL.strip() == "DEBUG":
+    FORMATTER = DEBUG_FORMAT
+
+
+def get_logger(log_handler_name, extra=EXTRA):
+    """
+    Purpose : To create logger .
+    :param log_handler_name: Name of the log handler.
+    :param extra: extra args for the logger
+    :return: logger object.
+    """
+    log_path = os.path.join(BASE_LOG_PATH, log_handler_name + ".log")
+    logstash_temp = os.path.join(BASE_LOG_PATH, log_handler_name + ".db")
+    logger = logging.getLogger(log_handler_name)
+    logger.setLevel(LOG_LEVEL.strip().upper())
+    log_handler = logging.StreamHandler()
+    log_handler.setLevel(LOG_LEVEL)
+    formatter = logging.Formatter(FORMATTER)
+    log_handler.setFormatter(formatter)
+    handler = RotatingFileHandler(log_path, maxBytes=10485760,
+                                  backupCount=5)
+    handler.setFormatter(formatter)
+    logger.addHandler(log_handler)
+    logger.addHandler(handler)
+
+    logger = logging.LoggerAdapter(logger, extra)
+    return logger
+
+
+logger = get_logger(LOG_HANDLER_NAME)
+

edge_engine/common/minio_server.py

+import os, time
+from minio import Minio
+from edge_engine.common.logsetup import logger
+
+
+class MinioClient:
+    def __init__(self ,SECRET_KEY, ACCESS_KEY, BUCKET_NAME, LOCAL_DATA_PATH, MINIO_IP):
+        logger.info("Initalizing minioclient !!")
+        self.SECRET_KEY = SECRET_KEY
+        self.ACCESS_KEY = ACCESS_KEY
+        self.BUCKET_NAME = BUCKET_NAME
+        self.LOCAL_DATA_PATH = LOCAL_DATA_PATH
+        self.MINIO_IP = MINIO_IP
+        self.logfile = "./logs/videowrite.log"
+        self.minioClient = self.connect_to_minio()
+        self.create_bucket(self.BUCKET_NAME)
+
+    def connect_to_minio(self):
+            if self.SECRET_KEY is not None and self.ACCESS_KEY is not None:
+                logger.info("Connecting to Minio Service... !!! ")
+                minio_client = Minio(self.MINIO_IP, access_key = self.ACCESS_KEY, secret_key = self.SECRET_KEY,
+                                    region='us-east-1', secure=False)
+                return minio_client
+            else:
+                logger.info('Access Key and Secret Key String cannot be null')
+                raise Exception('Access Key and Secret Key String cannot be null')
+
+
+    def create_bucket(self, bucket_name):
+        try:
+            if bucket_name not in self.list_buckets():
+                logger.info("Creating bucket {}...".format(bucket_name))
+                self.minioClient.make_bucket(bucket_name, location="us-east-1")
+            else:
+                logger.info("Bucket already exists....")
+        except Exception as err:
+            logger.error(err)
+
+    def save_to_bucket(self, bucket_name, data_obj):
+        try:
+            with open(data_obj, 'rb') as file:
+                file_stat = os.stat(data_obj)
+                self.minioClient.put_object(bucket_name, data_obj.split(self.LOCAL_DATA_PATH)[1],
+                                       file, file_stat.st_size)
+        except Exception as err:
+            logger.error(err)
+
+    def list_buckets(self):
+        bucketobjects = self.minioClient.list_buckets()
+        bucketlist = []
+        for eachbucket in bucketobjects:
+            bucketlist.append(eachbucket.name)
+        return bucketlist
+
+    def read_write_logs(self):
+        try:
+            f =  open(self.logfile)
+        except Exception as err:
+            print(err)
+            with open(self.logfile, "a") as startfile:
+                startfile.write("")
+            f = open(self.logfile)
+        return [line.split('\n')[0] for line in f]
+
+    def write_write_logs(self, log_str):
+        with open(self.logfile, "a") as my_file:
+            my_file.write(log_str + "\n")
+
+    def upload(self):
+        if self.LOCAL_DATA_PATH[-1]!='/':
+            self.LOCAL_DATA_PATH = self.LOCAL_DATA_PATH+"/"
+        while True:
+            listoffiles = [os.path.join(path, name) for path, subdirs, files in os.walk(self.LOCAL_DATA_PATH) for name in files]
+            listofwrittenfiles = self.read_write_logs()
+            listofnewfiles = list(set(listoffiles) - set(listofwrittenfiles))
+            for fileName in listofnewfiles:
+                try:
+                    logger.info("Uploading {}..".format(fileName.split(self.LOCAL_DATA_PATH)[1]))
+                    self.save_to_bucket(self.BUCKET_NAME, fileName)
+                    self.write_write_logs(fileName)
+                except Exception as e:
+                    logger.error(e)
+            time.sleep(5)
+
+# if __name__=='__main__':
+#     SECRET_KEY = 'minioadmin'
+#     ACCESS_KEY = 'minioadmin'
+#     BUCKET_NAME = 'videobucket'
+#     MINIO_IP = '192.168.3.220:29000'
+#     LOCAL_DATA_PATH = "F:/GDrive Data/Downloads"
+#     obj = MinioClient(SECRET_KEY, ACCESS_KEY, BUCKET_NAME, LOCAL_DATA_PATH, MINIO_IP)
+#     obj.upload()

edge_engine/edge_processor.py

+from edge_engine.common.logsetup import logger
+from edge_engine.common.config import EDGE_CONFIG
+from edge_engine.streamio.datastream import MQTT
+from edge_engine.streamio.datastream import VideoOutputStream
+from edge_engine.streamio.datastream import FrameOutputStream
+from edge_engine.streamio.datastream import FFMPEGOutputStream
+from edge_engine.streamio.datastream import MongoDataStreamOut
+from edge_engine.streamio.videostream import ThreadedVideoStream
+from edge_engine.streamio.videostream import FileVideoStream
+from edge_engine.streamio.frameProcessor import FrameProcessor, FrameProcessorv2
+from edge_engine.common.minio_server import MinioClient
+import json
+from threading import Thread
+import time
+import os
+
+from edge_engine.streamio.videostream.filepathvideostream import FilePathVideoStream
+
+class Pubs():
+
+    def __init__(self):
+        self.mqtt_pub = None
+        self.frame_write = None
+        self.video_write = None
+        self.mongo_write = None
+        self.rtp_write = None
+        self.build_pubs()
+        if 'minioConfig' in EDGE_CONFIG.keys()  and \
+                isinstance(EDGE_CONFIG["minioConfig"],dict):
+            self.minio_thread = self.start_minio(EDGE_CONFIG["minioConfig"])
+
+    @staticmethod
+    def start_minio(minio_conf):
+        obj = MinioClient(minio_conf['secretKey'], minio_conf['accessKey'],
+                          minio_conf['bucketName'], minio_conf['localDataPath'],
+                          minio_conf['ip'])
+        t = Thread(target=obj.upload)
+        t.start()
+        return t
+
+    def build_pubs(self):
+        logger.info("building publishers ")
+        for conf in EDGE_CONFIG["pubConfigs"]:
+            if conf["type"].upper() == "MQTT":
+                self.mqtt_pub = MQTT(broker=conf["broker"], topic=conf["topic"], port=conf["port"]
+                                     , publish_hook=json.dumps)
+
+            elif conf["type"].upper() == "FRAMEWRITE":
+                self.frame_write = FrameOutputStream(
+                    basepath=conf["basepath"],
+                    iformat=conf["iformat"],
+                    filenameFormat=conf["filenameFormat"],
+                    publish_hook=None)
+
+            elif conf["type"].upper() == "VIDEOWRITE":
+                self.video_write = VideoOutputStream(basepath=conf["basepath"],
+                                                     dims=conf["dims"],
+                                                     filenameFormat=conf["filenameFormat"],
+                                                     fps=conf["fps"], publish_hook=None)
+
+            elif conf["type"].upper() == "MONGO":
+                self.mongo_write = MongoDataStreamOut(host=conf["host"],
+                                                      port=conf["port"],
+                                                      dbname=conf["dbname"],
+                                                      collection=conf["collection"],
+                                                      keys=conf["keys"],
+                                                      authsource=conf["authSource"],
+                                                      username=conf["username"],
+                                                      password=conf["password"],
+                                                      publish_hook=None)
+            elif conf["type"].upper() == "RTP":
+                self.rtp_write = FFMPEGOutputStream(conf["ffmpegCmd"], conf["RTPEndpoint"]
+                                                    , publish_hook=None)
+            else:
+                logger.error("Unsupported publisher {}".format(conf["type"]))
+
+
+class ExecutePipeline:
+    def __init__(self, model,input_image):
+        self.model = model
+        self.input_image=input_image
+
+    def run_model(self):
+        if EDGE_CONFIG["inputConf"]["sourceType"].lower() in ["rtsp", "usbcam"]:
+            logger.info("Selected input stream as Direct cv input")
+            self.threadedVideoStream = ThreadedVideoStream(stream_config=EDGE_CONFIG["inputConf"])
+            self.threadedVideoStream.start()
+            self.frameProcessor = FrameProcessor(stream=self.threadedVideoStream,
+                                                 model=self.model)
+        elif EDGE_CONFIG["inputConf"]["sourceType"].lower() == "videofile":
+            self.fileVideoStream = FileVideoStream(stream_config=EDGE_CONFIG["inputConf"])
+            self.fileVideoStream.start()
+            self.frameProcessor = FrameProcessor(stream=self.fileVideoStream, model=self.model)
+
+        
+        elif EDGE_CONFIG["inputConf"]["sourceType"].lower() == "videopath":
+            processed_videos = []
+            videopath = EDGE_CONFIG["inputConf"].get('uri',"")
+            while True:
+                time1= time.time()
+
+                video_files = os.listdir(videopath)                
+                if not video_files:
+                    time.sleep(0.01)
+                    continue
+                video_files.sort()
+                for video in video_files:
+                    if video in processed_videos:
+                        continue
+                    if not video.endswith(".mp4"):
+                        processed_videos.append(video)
+                        continue
+                                      
+                    processed_videos.append(video)
+                    
+                    EDGE_CONFIG["inputConf"]['uri'] = os.path.join(videopath, video)
+                    self.fileVideoStream = FilePathVideoStream(EDGE_CONFIG["inputConf"]['uri'])
+                    self.fileVideoStream.start()
+                    self.frameProcessor = FrameProcessorv2(stream=self.fileVideoStream, model=self.model)
+                    self.start_model()
+                    logger.info("---------------")
+                    logger.info(time.time()-time1)
+                    # logger.info(int(time.time())-time2)
+                    # logger.info(int(time.time())-time3)
+                    logger.info("---------------")
+        elif EDGE_CONFIG["inputConf"]["sourceType"].lower() == "api_call":
+            processed_images = []
+            # imagepath = EDGE_CONFIG["inputConf"].get('uri', "")
+            # # while True:
+            #     #write
+            # time1 = time.time()
+            #
+            # image_files = os.listdir(imagepath)
+            # # if not image_files:
+            # #     time.sleep(0.01)
+            # #     continue
+            # image_files.sort()
+            # for images in image_files:
+            #     if images in processed_images:
+            #         continue
+            #     if not images.endswith(".jpg"):
+            #         processed_images.append(images)
+            #         continue
+            #     print(images)
+            #
+            #     processed_images.append(images)
+
+                # EDGE_CONFIG["inputConf"]['uri'] = os.path.join(imagepath, images)
+                # print(EDGE_CONFIG["inputConf"]['uri'])
+                # self.fileVideoStream = FilePathVideoStream(EDGE_CONFIG["inputConf"]['uri'])
+            self.frameProcessor = FrameProcessorv2(stream=self.input_image, model=self.model)
+            self.start_model()
+            logger.info("---------------")
+            # logger.info(time.time() - time1)
+            # logger.info(int(time.time())-time2)
+            # logger.info(int(time.time())-time3)
+            logger.info("---------------")
+
+
+        else:
+            raise ValueError("unsupported source  {}".format(EDGE_CONFIG["inputConf"]["sourceType"]))
+
+        self.start_model()
+
+    def start_model(self):
+        self.frameProcessor.run_model()
+        # self.thread = Thread(target=self.frameProcessor.run_model(), args=())
+        # print("running start model")
+        # self.thread.daemon = True
+        # self.thread.start()

edge_engine/streamio/__init__.py

+from edge_engine.streamio.frameProcessor import FrameProcessor
+from .datastreamprocessor import DataStreamProcessor

edge_engine/streamio/datastream/__init__.py

+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+from edge_engine.streamio.datastream.mongodatastreamout import MongoDataStreamOut
+from edge_engine.streamio.datastream.frameoutputstream import FrameOutputStream
+from edge_engine.streamio.datastream.videooutputstream import VideoOutputStream
+from edge_engine.streamio.datastream.mqttstream import MQTT
+from edge_engine.streamio.datastream.ffmpegdata_streamout import FFMPEGOutputStream
\ No newline at end of file

edge_engine/streamio/datastream/datastreamwrapper.py

+from abc import ABC, abstractmethod
+
+
+class DataStreamWrapper(ABC):
+    def __init__(self):
+        """Implement code to load mask_model here"""
+        pass
+
+    def publish(self, x):
+        """Implement code to publish"""
+        return x
+
+    def subscribe(self,hook):
+        """Implement code to subscribe"""
+        return None
\ No newline at end of file

edge_engine/streamio/datastream/ffmpegdata_streamout.py

+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+import subprocess as sp
+
+
+class FFMPEGOutputStream(DataStreamWrapper):
+
+    def __init__(self, ffmpeg_cmd, rtp_endpoint, publish_hook=None):
+        super().__init__()
+        self.ffmpeg_cmd = ffmpeg_cmd
+        self.rtp_endpoint = rtp_endpoint
+        self.ffmpeg_cmd.append(self.rtp_endpoint[0])
+        self.proc = sp.Popen(self.ffmpeg_cmd, stdin=sp.PIPE, shell=False)
+        self.publish_hook = publish_hook
+
+    def publish(self, x):
+        if self.publish_hook is not None:
+            x = self.publish_hook(x)
+        # print("value of x:  ",x)
+
+        # print("value:",x)
+        frame = x["frame"]
+
+        self.proc.stdin.write(frame.tostring())
+        self.proc.stdin.flush()

edge_engine/streamio/datastream/frameoutputstream.py

+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+import cv2
+import base64
+import numpy as np
+import os
+from edge_engine.common.logsetup import logger
+from datetime import datetime
+
+
+class FrameOutputStream(DataStreamWrapper):
+    def __init__(self, basepath, iformat="jpg", filenameFormat="{deviceId}_{frameId}_{timestamp}", publish_hook=None):
+        super().__init__()
+        self.basepath = basepath
+        self.iformat = iformat
+        self.filenameFormat = filenameFormat
+        self.publish_hook = publish_hook
+
+
+    def publish(self, x):
+        if self.publish_hook is not None:
+            x= self.publish_hook(x)
+        frame = x["frame"]
+        # frame = base64.b64decode(frame.split("data:image/jpeg;base64,")[1])
+        # frame = np.fromstring(frame, np.uint8)
+        # frame = cv2.imdecode(frame, cv2.IMREAD_COLOR)
+        path = os.path.join(self.basepath, datetime.now().date().isoformat())
+        print("path :    ",path)
+        if not os.path.isdir(path):
+            logger.info("Creating {}  \n".format(path))
+            os.mkdir(path)
+        cv2.imwrite("{path}.{iformat}".format(path=os.path.join(path, self.filenameFormat.format(**x)),
+                                              iformat=self.iformat), frame)
+        return True
+
+    def subscribe(self, hook):
+        super().subscribe(hook)

edge_engine/streamio/datastream/mongodatastreamout.py

+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+from pymongo import MongoClient
+
+
+class MongoDataStreamOut(DataStreamWrapper):
+
+    def __init__(self, host, port, dbname, collection, keys, authsource,username=None,password=None, publish_hook=None):
+        super().__init__()
+        self.host = host
+        self.port = port
+        self.dbname = dbname
+        self.username = username
+        self.password = password
+        self.collection = collection
+        self.publish_hook = publish_hook
+        self.mongo = MongoClient(host=host,
+                                 port=int(port),username=self.username,password=self.password)
+        self.db = self.mongo[dbname]
+        self.keys = keys
+        self.authsource = authsource
+
+    def subscribe(self, hook=None):
+        pass
+
+    def publish(self, data):
+        if self.publish_hook is not None:
+            data = self.publish_hook(data)
+        fin_dat = {}
+        for k, v in data.items():
+            if k in self.keys:
+                fin_dat[k] = v
+        self.db[self.collection].insert(fin_dat)

edge_engine/streamio/datastream/mqttstream.py

+import paho.mqtt.client as paho
+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+from edge_engine.common.logsetup import logger
+from uuid import uuid4
+import traceback
+class MQTT(DataStreamWrapper):
+    @staticmethod
+    def on_connect(client, userdata, flags, rc):
+        logger.info("Connection returned with result code:" + str(rc))
+
+    @staticmethod
+    def on_disconnect(client, userdata, rc):
+        logger.info("Disconnection returned result:" + str(rc))
+
+    @staticmethod
+    def on_subscribe(client, userdata, mid, granted_qos):
+        logger.debug("Subscribing MQTT {} {} {} {}".format(client, userdata, mid, granted_qos))
+
+    def on_message(self, client, userdata, msg):
+        logger.debug("Received message, topic:" + msg.topic + "payload:" + str(msg.payload))
+        if self.subscribe_hook is not None:
+            self.subscribe_hook(msg.payload.decode())
+
+    def __init__(self, broker, port, topic, qos=2, subscribe_hook=None, publish_hook=None):
+        super().__init__()
+        self.broker = broker
+        self.port = int(port)
+        self.topic = topic
+        self.client_name = "{}".format(uuid4())
+        self.client = paho.Client(self.client_name)
+        self.client.on_connect = self.on_connect
+        self.client.on_disconnect = self.on_disconnect
+        self.client.on_subscribe = self.on_subscribe
+        self.client.on_message = self.on_message
+        self.client.connect(host=self.broker, port=self.port)
+        self.subscribe_hook = subscribe_hook
+        self.publish_hook = publish_hook
+        self.qos = qos
+
+    def subscribe(self, hook=None):
+        if hook is not None:
+            self.subscribe_hook =hook
+        self.client.subscribe((self.topic, self.qos))
+        self.client.loop_forever()
+
+    def publish(self, data):
+        try:
+            if self.publish_hook is not None:
+                data = self.publish_hook(data)
+            self.client.publish(self.topic, data)
+        except Exception as e:
+            logger.error(e)
+            logger.error(traceback.format_exc())

edge_engine/streamio/datastream/videooutputstream.py

+from edge_engine.streamio.datastream.datastreamwrapper import DataStreamWrapper
+import cv2
+import base64
+import numpy as np
+import os
+from edge_engine.common.logsetup import logger
+from datetime import datetime
+
+
+class VideoOutputStream(DataStreamWrapper):
+    def __init__(self, basepath, dims, filenameFormat="{deviceId}_{timestamp}", fps=30, publish_hook=None):
+        super().__init__()
+        self.basepath = basepath
+        self.dims = (int(dims[0]),int(dims[1]))
+        self.fps = float(fps)
+        self.filenameFormat = filenameFormat
+        self.publish_hook = publish_hook
+        self.four_cc = cv2.VideoWriter_fourcc(*'mp4v')
+        self.out = None
+
+    def publish(self, x):
+        if self.publish_hook is not None:
+            x = self.publish_hook(x)
+        if len(x["metric"]) > 0:
+            if self.out is None:
+                path = os.path.join(self.basepath, datetime.now().date().isoformat())
+                if not os.path.isdir(path):
+                    logger.info("Creating {}  \n".format(path))
+                    os.mkdir(path)
+                self.out = cv2.VideoWriter("{}.mp4".format(os.path.join(path, self.filenameFormat.format(**x))),
+                                           self.four_cc, self.fps, self.dims)
+            frame = x["frame"]
+            frame = base64.b64decode(frame.split("data:image/jpeg;base64,")[1])
+            frame = np.fromstring(frame, np.uint8)
+            frame = cv2.imdecode(frame, cv2.IMREAD_COLOR)
+            self.out.write(frame)
+        else:
+            if self.out  is not None:
+                self.out.release()
+                self.out = None
+        return True
+
+    def subscribe(self, hook):
+        super().subscribe(hook)

edge_engine/streamio/datastreamprocessor.py

+from edge_engine.common.logsetup import logger
+
+
+class DataStreamProcessor:
+    def __init__(self, model, subsciber, publishers=list()):
+        self.model = model
+        self.subsciber = subsciber
+        self.publishers = publishers
+        logger.info("Setting up frame processor !!")
+
+    def processstream(self, msg):
+        print(msg)
+
+    def run_model(self):
+        self.subsciber.subscribe(hook=self.processstream)

edge_engine/streamio/frameProcessor.py

+import time
+
+from edge_engine.common.logsetup import logger
+from edge_engine.common.config import DEVICE_ID
+from uuid import uuid4
+import traceback
+import cv2
+
+class FrameProcessor:
+    def __init__(self, stream, model):
+        self.model = model
+        self.stream = stream
+        logger.info("Setting up frame processor !!")
+        self.count = 0
+        self.skip_frame_every = 1  # 1 does not skip any frame (n-1 frames get skipped)
+
+
+    def run_model(self):
+        while self.stream.stream.isOpened():
+            try:
+                logger.debug("Getting frame mask_model")
+                frame = self.stream.read()
+                logger.debug("Running mask_model")
+                self.count += 1
+                # print("count.......",self.count)
+                if frame is not None and self.count % self.skip_frame_every == 0:
+                    fid = uuid4()
+                    data = {
+                        "frame": frame,
+                        "frameId": "{}".format(fid),
+                        "deviceId": "{}".format(DEVICE_ID),
+                    }
+
+                    self.model.predict(data)
+                time.sleep(0.01)
+            except Exception as e:
+                logger.error(e)
+                logger.error(traceback.format_exc())
+
+
+class FrameProcessorv2:
+    def __init__(self, stream, model):
+        self.model = model
+        self.stream = stream
+        self.count = 0
+        self.skip_frame_every = 3  # 1 does not skip any frame (n-1 frames get skipped)
+
+    def run_model(self):
+        try:
+            frame = self.stream
+            # print("steam",type(frame))
+            self.count += 1
+            if frame is not None:
+                fid = uuid4()
+                data = {
+                    "frame": frame,
+                    "frameId": "{}".format(fid),
+                    "deviceId": "{}".format(DEVICE_ID),
+                }
+
+                self.model.predict(data)
+
+        except Exception as e:
+            logger.error(e)
+            logger.error(traceback.format_exc())
+
+
+

edge_engine/streamio/videostream/__init__.py

+from edge_engine.streamio.videostream.fps import FPS
+from edge_engine.streamio.videostream.nvgstreamer import NVGstreamer
+from edge_engine.streamio.videostream.simplevideostream import SimpleVideoStream
+from edge_engine.streamio.videostream.threadedvideostream import ThreadedVideoStream
+from edge_engine.streamio.videostream.filevideostream import FileVideoStream
\ No newline at end of file

edge_engine/streamio/videostream/filepathvideostream.py

+# import the necessary packages
+from threading import Thread
+import sys
+import cv2
+import time
+import os
+import shutil
+import imutils
+
+# import the Queue class from Python 3
+if sys.version_info >= (3, 0):
+    from queue import Queue
+
+# otherwise, import the Queue class for Python 2.7
+else:
+    from Queue import Queue
+
+
+def frame_transform(frame):
+    frame = imutils.resize(frame, width=416, height=416)
+    return frame
+
+class FilePathVideoStream:
+    def __init__(self, path, transform=None, queue_size=256):
+        # initialize the file video stream along with the boolean
+        # used to indicate if the thread should be stopped or not
+        self.path=path
+        self.stream=cv2.imread(path)
+        # while True:
+        #     self.stream = cv2.VideoCapture(path)
+        #     if not self.stream.isOpened():
+        #         time.sleep(0.01)
+        #         continue
+        #     break
+        self.stopped = False
+        self.transform = transform
+
+        # initialize the queue used to store frames read from
+        # the video file
+        # self.Q = Queue(maxsize=queue_size)
+        # intialize thread
+        self.thread = Thread(target=self.update, args=())
+        self.thread.daemon = True
+
+    def start(self):
+        # start a thread to read frames from the file video stream
+        self.thread.start()
+        return self
+
+    def update(self):
+        # keep looping infinitely
+        while True:
+            # if the thread indicator variable is set, stop the
+            # thread
+            if self.stopped:
+                break
+
+            # otherwise, ensure the queue has room in it
+
+
+            frame=self.stream
+            grabbed=True
+
+            if  grabbed:
+                self.stopped = True
+
+            if self.transform:
+                frame = self.transform(frame)
+                return frame
+
+
+                # add the frame to the queue
+
+            else:
+                time.sleep(0.1)  # Rest for 10ms, we have a full queue
+
+        # self.stream.release()
+
+    def read(self):
+        # return next frame in the queue
+        return self.Q.get()
+
+    # Insufficient to have consumer use while(more()) which does
+    # not take into account if the producer has reached end of
+    # file stream.
+    def running(self):
+        # custom addition to this func
+        cond = self.more() or not self.stopped
+        if not cond:
+            self.move_file()
+        return cond
+
+    def more(self):
+        # return True if there are still frames in the queue. If stream is not stopped, try to wait a moment
+        tries = 0
+        while self.Q.qsize() == 0 and not self.stopped and tries < 5:
+            time.sleep(0.1)
+            tries += 1
+
+        return self.Q.qsize() > 0
+
+    def stop(self):
+        # indicate that the thread should be stopped
+        self.stopped = True
+        # wait until stream resources are released (producer thread might be still grabbing frame)
+        self.thread.join()
+        
+    def move_file(self):
+        src_path = self.path
+        dest_path = "archive"
+        root_path = os.path.dirname(os.path.abspath(__file__))
+        src = os.path.join(root_path, src_path)
+        if not os.path.exists(dest_path):
+            os.mkdir(dest_path)
+        shutil.move(src, dest_path)

edge_engine/streamio/videostream/filevideostream.py

+# import the necessary packages
+from threading import Thread
+import sys
+import cv2
+import time
+# import the Queue class from Python 3
+if sys.version_info >= (3, 0):
+    from queue import Queue
+
+# otherwise, import the Queue class for Python 2.7
+else:
+    from Queue import Queue
+
+
+class FileVideoStream:
+    def __init__(self,stream_config, transform=None):
+        # initialize the file video stream along with the boolean
+        # used to indicate if the thread should be stopped or not
+        self.transform = transform
+        self.stream_config =stream_config
+        # initialize the queue used to store frames read from
+        # the video file
+        self.build_pipeline()
+
+
+    def start(self):
+        # start a thread to read frames from the file video stream
+        self.thread.start()
+        return self
+
+    def build_cv_obj(self):
+        self.stream = cv2.VideoCapture(self.stream_config["uri"])
+        self.stopped = False
+
+    def build_pipeline(self):
+        self.build_cv_obj()
+        if "queueSize" not in self.stream_config:
+            self.stream_config["queueSize"] =128
+
+        self.Q = Queue(maxsize=int(self.stream_config["queueSize"]))
+        # intialize thread
+        self.thread = Thread(target=self.update, args=())
+        self.thread.daemon = True
+
+
+    def is_opened(self):
+        return self.stream.isOpened()
+
+    def update(self):
+        # keep looping infinitely
+        while True:
+            # if the thread indicator variable is set, stop the
+            # thread
+            if self.stopped:
+                break
+
+            # otherwise, ensure the queue has room in it
+            if not self.Q.full():
+                # read the next frame from the file
+                (grabbed, frame) = self.stream.read()
+
+                # if the `grabbed` boolean is `False`, then we have
+                # reached the end of the video file
+                if grabbed is False or frame is None:
+                    #self.stopped = True
+                    self.build_cv_obj()
+                    continue
+
+                # if there are transforms to be done, might as well
+                # do them on producer thread before handing back to
+                # consumer thread. ie. Usually the producer is so far
+                # ahead of consumer that we have time to spare.
+                #
+                # Python is not parallel but the transform operations
+                # are usually OpenCV native so release the GIL.
+                #
+                # Really just trying to avoid spinning up additional
+                # native threads and overheads of additional
+                # producer/consumer queues since this one was generally
+                # idle grabbing frames.
+                if self.transform:
+                    frame = self.transform(frame)
+
+                # add the frame to the queue
+                self.Q.put(frame)
+            else:
+                time.sleep(0.1)  # Rest for 10ms, we have a full queue
+
+        self.stream.release()
+
+    def read(self):
+        # return next frame in the queue
+        return self.Q.get()
+
+    # Insufficient to have consumer use while(more()) which does
+    # not take into account if the producer has reached end of
+    # file stream.
+    def running(self):
+        return self.more() or not self.stopped
+
+    def more(self):
+        # return True if there are still frames in the queue. If stream is not stopped, try to wait a moment
+        tries = 0
+        while self.Q.qsize() == 0 and not self.stopped and tries < 5:
+            time.sleep(0.1)
+            tries += 1
+
+        return self.Q.qsize() > 0
+
+    def stop(self):
+        # indicate that the thread should be stopped
+        self.stopped = True
+        # wait until stream resources are released (producer thread might be still grabbing frame)
+        self.thread.join()
\ No newline at end of file

edge_engine/streamio/videostream/fps.py

+# import the necessary packages
+import datetime
+
+
+class FPS:
+    def __init__(self):
+        # store the start time, end time, and total number of frames
+        # that were examined between the start and end intervals
+        self._start = None
+        self._end = None
+        self._numFrames = 0
+
+    def start(self):
+        # start the timer
+        self._start = datetime.datetime.now()
+        return self
+
+    def stop(self):
+        # stop the timer
+        self._end = datetime.datetime.now()
+
+    def update(self):
+        # increment the total number of frames examined during the
+        # start and end intervals
+        self._numFrames += 1
+
+    def elapsed(self):
+        # return the total number of seconds between the start and
+        # end interval
+        return (self._end - self._start).total_seconds()
+
+    def fps(self):
+        # compute the (approximate) frames per second
+        return self._numFrames / self.elapsed()

edge_engine/streamio/videostream/nvgstreamer.py

+import cv2
+
+
+class NVGstreamer:
+
+    def __init__(self, buildconfig):
+        self.width = 480
+        self.height = 640
+        self.latency = 0
+        self.framerate = "10/1"
+        self.fformat = "BGRx"
+
+        self.BUILD_CONFIG = {
+            "width": self.width,
+            "height": self.height,
+            "latency": self.latency,
+            "framerate": self.framerate,
+            "format": self.fformat,
+            "gstreamer": True
+        }
+
+        self.BUILD_CONFIG.update(buildconfig)
+
+    def open_cam_rtsp(self):
+        gst_str = ('rtspsrc location={uri} latency={latency} ! '
+                   'rtph264depay ! h264parse ! omxh264dec ! '
+                   'nvvidconv ! videorate ! '
+                   'video/x-raw, width=(int){width}, height=(int){height}, '
+                   'format=(string){format}, framerate=(fraction){framerate} ! '
+                   'videoconvert ! appsink').format(**self.BUILD_CONFIG)
+        print(gst_str)
+        return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)
+
+    def open_cam_usb(self):
+        # We want to set width and height here, otherwise we could just do:
+        #     return cv2.VideoCapture(dev)
+        gst_str = ('v4l2src device=/dev/video{uri} ! '
+                   'video/x-raw, width=(int){width}, height=(int){height}, '
+                   'format=(string){format}, framerate=(fraction){framerate} ! '
+                   'videoconvert ! appsink').format(**self.BUILD_CONFIG)
+        print(gst_str)
+        return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)
+
+    def open_cam_onboard(self):
+        # On versions of L4T prior to 28.1, add 'flip-method=2' into gst_str
+        gst_str = ('nvcamerasrc ! '
+                   'video/x-raw(memory:NVMM), '
+                   'width=(int)2592, height=(int)1458, '
+                   'format=(string)I420 ! '
+                   'nvvidconv ! videorate ! '
+                   'video/x-raw, width=(int){width}, height=(int){height}, '
+                   'format=(string){format}, framerate=(fraction){framerate} !'
+                   'videoconvert ! appsink').format(**self.BUILD_CONFIG)
+        print(gst_str)
+        return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)
+
+    def custom_pipeline(self):
+        gst_str = "{customGstPipelineString}".format(**self.BUILD_CONFIG)
+        print(gst_str)
+        return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)
+
+    def build_pipeline(self):
+        if self.BUILD_CONFIG["gStreamer"]!=True:
+            if  self.BUILD_CONFIG["sourceType"] == "usbcam":
+                self.cap = cv2.VideoCapture(int(self.BUILD_CONFIG["uri"]))
+            else:
+                self.cap = cv2.VideoCapture(self.BUILD_CONFIG["uri"])
+        elif self.BUILD_CONFIG["sourceType"] == "rtsp":
+            self.cap = self.open_cam_rtsp()
+        elif self.BUILD_CONFIG["sourceType"] == "usbcam":
+            self.cap = self.open_cam_usb()
+        elif self.BUILD_CONFIG["sourceType"] == "onboard":
+            self.cap = self.open_cam_onboard()
+        elif self.BUILD_CONFIG["sourceType"] == "customPipeline":
+            self.cap = self.custom_pipeline()
+        else:
+            raise ValueError("unimplemented source {}".format(self.BUILD_CONFIG["sourceType"]))
+
+    def get_stream(self):
+        return self.cap

edge_engine/streamio/videostream/simplevideostream.py

+from edge_engine.common.logsetup import logger
+from edge_engine.streamio.videostream import NVGstreamer
+
+
+class SimpleVideoStream:
+    def __init__(self, stream_config, name="SimpleVideoStream"):
+        self.stream_config = stream_config
+        self.build_pipeline()
+        (self.grabbed, self.frame) = self.stream.read()
+        self.name = name
+
+    def build_pipeline(self):
+        self.gstreamer = NVGstreamer(self.stream_config)
+        self.gstreamer.build_pipeline()
+        self.stream = self.gstreamer.get_stream()
+
+    def start(self):
+        logger.info("Starting video stream ")
+        if self.stream.isOpened():
+            self.grabbed, self.frame = self.stream.read()
+            if self.grabbed is False:
+                logger.error("Empty Frame !!!! ")
+                logger.error("Error opening Capture !!!! ")
+                self.build_pipeline()
+            return self
+        else:
+            logger.error("Error opening Capture !!!! ")
+            self.build_pipeline()
+
+    def is_opened(self):
+        return self.stream.isOpened()
+
+    def read(self):
+        # return the frame most recently read
+        if self.stream.isOpened():
+            self.grabbed, self.frame = self.stream.read()
+            if self.grabbed is False:
+                logger.error("Empty Frame !!!! ")
+                raise ValueError("Empty Frame !!!! ")
+            return self.frame
+        else:
+            logger.error("Error opening Capture !!!! ")
+            raise ValueError("Error opening Capture !!!! ")
+
+    def stop(self):
+        if self.stream.isOpened():
+            self.stream.release()

edge_engine/streamio/videostream/threadedvideostream.py

+# import the necessary packages
+from threading import Thread
+import time
+from edge_engine.streamio.videostream import NVGstreamer
+from edge_engine.common.logsetup import logger
+
+
+class ThreadedVideoStream:
+    def __init__(self, stream_config, name="ThreadedVideoStream"):
+        # initialize the video camera stream and read the first frame
+        # from the stream
+        self.stream_config = stream_config
+        self.build_pipeline()
+        # self.stream = stream
+        (self.grabbed, self.frame) = self.stream.read()
+        # initialize the thread name
+        self.name = name
+
+        # initialize the variable used to indicate if the thread should
+        # be stopped
+        self.stopped = False
+
+    def build_pipeline(self):
+        self.gstreamer = NVGstreamer(self.stream_config)
+        self.gstreamer.build_pipeline()
+        self.stream = self.gstreamer.get_stream()
+
+    def start(self):
+        # start the thread to read frames from the video stream
+        t = Thread(target=self.update, name=self.name, args=())
+        t.daemon = True
+        t.start()
+        return self
+
+    def update(self):
+        # keep looping infinitely until the thread is stopped
+        while True:
+            # if the thread indicator variable is set, stop the thread
+            if self.stopped:
+                return
+
+            # otherwise, read the next frame from the stream
+            (self.grabbed, self.frame) = self.stream.read()
+            if self.grabbed is False or self.frame is None:
+                logger.error("Empty Frame !!!! ")
+                logger.error("Error opening Capture !!!! ")
+                self.build_pipeline()
+
+    def read(self):
+        # return the frame most recently read
+        return self.frame
+
+    def stop(self):
+        # indicate that the thread should be stopped
+        self.stopped = True
+        time.sleep(0.2)
+        self.stream.release()

edge_engine/version.py

+# Copyright 2019 KnowledgeLens pvt Ltd.
+
+
+VERSION = '0.0.1.alpha'

requirements.txt

+opencv-python==4.5.5.62
+#pycuda==2020.1
+numpy==1.19.4
+requests>=2.23.0
+expiringdict==1.2.1
+minio==7.1.3
+cachetools==4.2.4
+pymongo==4.0.1
+Cython==0.29.21
+paho-mqtt==1.5.0
+scikit-learn==0.22.2.post1
+python-dateutil==2.8.2
+imutils==0.5.4
\ No newline at end of file

scripts/__init__.py

+from.cement_counter import CementBagCounter
\ No newline at end of file

scripts/cement_counter.py

+import cv2
+import base64
+import numpy as np
+from scipy.spatial import distance
+from expiringdict import ExpiringDict
+import time
+from edge_engine.common.logsetup import logger
+from scripts.utils.infocenter import MongoLogger
+from yolov5processor.infer import ExecuteInference
+from scripts.utils.edge_utils import get_extra_fields
+from edge_engine.ai.model.modelwraper import ModelWrapper
+from scripts.utils.centroidtracker import CentroidTracker
+from scripts.common.constants import JanusDeploymentConstants
+from scripts.utils.image_utils import draw_circles_on_frame, resize_to_64_64
+from pymongo import MongoClient
+from scripts.common.config import MONGO_URI
+from uuid import uuid4
+import cv2
+import base64
+import datetime
+import numpy as np
+import imutils
+from collections import deque
+from expiringdict import ExpiringDict
+from scipy.optimize import linear_sum_assignment as linear_assignment
+
+from edge_engine.common.logsetup import logger
+from edge_engine.ai.model.modelwraper import ModelWrapper
+
+from scripts.utils.tracker import Tracker
+from scripts.utils.helpers import box_iou2
+from scripts.utils.edge_utils import Utilities
+from scripts.utils.infocenter import MongoLogger
+from scripts.utils.model_tracker import ModelCountTracker
+from scripts.common.constants import JanusDeploymentConstants
+
+from yolov5processor.infer import ExecuteInference
+from scripts.utils.relay_util import RelayHandler
+from paddleocr import PaddleOCR
+
+
+class CementBagCounter(ModelWrapper):
+    def __init__(self, config, model_config, pubs, device_id):
+        super().__init__()
+        """
+        init function
+        """
+        self.config = config["config"]
+        self.device_id = device_id
+        self.rtp = pubs.rtp_write
+        self.mongo_logger = MongoLogger()
+        self.frame_skip = self.config.get("frame_skip", False)
+        # model = "data/acc_v13.pt"
+        # self.yp = ExecuteInference(
+        #     weight=model,
+        #     gpu=model_config.get("gpu", False),
+        #     agnostic_nms=model_config.get("agnostic_nms", True),
+        #     iou=model_config.get("iou", 0.2),
+        #     confidence=model_config.get("confidence", 0.3),
+        #     img_size=640,
+        # )
+        # self.print_eu_dist = model_config.get("print_eu_dist", 200)
+        # self.ct1 = CentroidTracker(maxDisappeared=5)
+        # self.ct2 = CentroidTracker(maxDisappeared=5)
+
+        self.count = 0
+        self.cement_bag = 0
+        self.count_suraksha = 0
+        self.count_whitecem = 0
+        self.count_gold = 0
+        self.tracker_list = []
+        self.max_age = 3
+        self.min_hits = 0
+        self.track_id_list = deque([str(i) for i in range(1, 50)])
+        self.prev_annotation = []
+        self.mrp_counter = 0
+        self.count_nfr = 0
+        self.count_suraksha_power = 0
+        self.count_concrete_plus = 0
+        self.count_ambuja_plus = 0
+        self.text = " "
+        self.mrp_text = " "
+        self.recognition_output_list = []
+        self.recognition_output=""
+        # self.prev_class_name = None
+        self.plant_name = ["R"]
+        self.year_front_axle_bar_and_engine = ["B","C","D","E","F","G","H","I","J","K","L","M","N","O","P","Q","R","S","T","U","V","W","X","Y","Z","1","2","3","4"]
+        self.fixed = ["M","B","N"]
+        self.internal_engine = ["2", "K", "G", "A"]
+        self.internal =["T","F","A","E","X","A"]
+        self.internal_front_axle_bar_2  = ["A","B","A","C","A","A"]
+        self.internal_front_axle_bar = ["T","F","A","E","X","A"]
+        # self.fixed_and_internal_front_axle_bar_2 = ["M", "B", "N", "A", "B", "A", "C", "A", "A"]
+        self.fixed_and_internal_engine = ["2", "K", "C", "A"]
+        self.month_engine = ["K","L","M","A","B","C","D","E","F","G","H","J"]
+        self.month_front_axle_bar = ["A","B","C","D","E","F","G","H","I","J","K","L","M"]
+        self.text_json = {"data":{"text":" ", "fixed characters":" ", "internal characters": " ", "year": " ", "month": " ", "plant": " ", "serial number": " "}, "status": False, "message": " "}
+
+        self.initial_object_position = None
+
+        self.uncounted_objects = ExpiringDict(
+            max_len=model_config.get("uncounted_obj_length", 50),
+            max_age_seconds=model_config.get("uncounted_obj_age", 60),
+        )
+        self.janus_metadata = ExpiringDict(max_age_seconds=120, max_len=1)
+        self.mongo_alarm_coll = MongoClient(MONGO_URI)["ilens_events"][
+            "triggered_alarms"
+        ]
+        self.camera_details = self.mongo_logger.get_camera_details(self.device_id)
+        self.ocr=self.paddle_ocr_load_model()
+        # self.black_to_white_dict = get_extra_fields(self.device_id).get(
+        #     JanusDeploymentConstants.BLACK_WHITE_RATIO
+        # )
+
+
+    def _pre_process(self, x):
+        """
+        Do preprocessing here, if any
+        :param x: payload
+        :return: payload
+        """
+        return x
+
+    def _post_process(self, x):
+        """
+        Apply post processing here, if any
+        :param x: payload
+        :return: payload
+        """
+        self.rtp.publish(x)  # video stream
+        return x
+
+    def send_payload(
+        self,
+        frame,
+        bag_type="",
+        label="CementBagDetected",
+        bg_color="#474520",
+        font_color="#FFFF00",
+        alert_sound=None,
+        message="Cement Bag Detected!",
+        mrp="FAIL",
+        mrp_frmae="",
+        mrp_roi="",
+        mrp_check_result="",
+    ):
+        """
+        Insert event to Mongo
+        :param message:
+        :param frame:
+        :param label:
+        :param bg_color:
+        :param font_color:
+        :param alert_sound:
+        :return: None
+        """
+
+        payload = {
+            "deviceId": self.device_id,
+            "message": message,
+            "frame": "data:image/jpeg;base64,"
+            + base64.b64encode(cv2.imencode(".jpg", frame)[1].tostring()).decode(
+                "utf-8"
+            ),
+            "activity": label,
+            "bg_color": bg_color,
+            "font_color": font_color,
+            "alert_sound": alert_sound,
+            "bag_type": bag_type,
+            "mrp_frmae": mrp_frmae,
+            "mrp_roi": mrp_roi,
+            "mrp_digit_check": mrp_check_result,
+            "mrp": mrp
+        }
+
+        self.mongo_logger.insert_attendance_event_to_mongo(payload)
+
+    def paddle_ocr_load_model(self):
+        ocr = PaddleOCR(
+            lang="en",
+            # det_db_thresh=0.1,
+            # det_db_box_thresh=0.1,
+            # use_mp=True,
+            # total_process_num=process_count,
+            use_angle_cls=True,
+            cls_model_dir="paddleocr/model/ch_ppocr_mobile_v2.0_cls_infer",
+            rec_model_dir="paddleocr/model/ch_PP-OCRv3_rec_infer",
+            det_model_dir="paddleocr/model/en_PP-OCRv3_det_infer")
+        return ocr
+    def paddle_ocr_predict(self,ocr,img_path):
+
+        result = ocr.ocr(img_path, cls=False, det=True, rec=True)[0]
+        txts = [line[1][0] for line in result]
+        return txts[0]
+
+    def check_character(self,character):
+        if len(character) == 17:
+            return "front_axle_bar"
+        elif len(character) == 13:
+            return "engine"
+
+        else:
+            return False
+    def fixed_char_check(self, text_list, part_name):
+        if(part_name == "front_axle_bar"):
+            sub_list = text_list[0:3]
+            # print(sub_list)
+            matching_chars = [i for i, j in zip(sub_list, self.fixed) if i == j]
+            # matching_chars_2 = [i for i, j in zip(sub_list, self.fixed_and_internal_front_axle_bar_2) if i == j]
+            # print(matching_chars)
+            if(len(matching_chars) > 1):
+                return True
+            return False
+
+        else:
+
+            return True
+    def internal_char_check(self, text_list, part_name):
+        if(part_name == "front_axle_bar"):
+            sub_list = text_list[3:9]
+            # print(sub_list)
+            matching_chars = [i for i, j in zip(sub_list, self.internal_front_axle_bar) if i == j]
+            matching_chars_2 = [i for i, j in zip(sub_list, self.internal_front_axle_bar_2) if i == j]
+            # print(matching_chars)
+            if(len(matching_chars) > 3):
+                return True, "front axle_bar"
+            if (len(matching_chars_2) > 3):
+                return True, "front axle bar 2"
+            return False, None
+        else:
+            sub_list = text_list[3:7]
+            # print(sub_list)
+            matching_chars = [i for i, j in zip(sub_list, self.internal_engine) if i == j]
+            # print(matching_chars)
+            if (len(matching_chars) < 3):
+                return False, None
+            return True, None
+
+
+    def plant_ver(self, text_list, part_name):
+        if (part_name == "front_axle_bar"):
+
+            plant_char = text_list[10]
+            if (plant_char != "R"):
+                return False
+            return True
+
+        else:
+            plant_char = text_list[0]
+            if (plant_char != "R"):
+                return False
+            return True
+    def year_ver(self, text_list, part_name):
+        if (part_name == "front_axle_bar"):
+
+            year_char = text_list[9]
+            if (year_char not in self.year_front_axle_bar_and_engine):
+                return False
+            return True
+
+        else:
+            year_char = text_list[1]
+            if (year_char not in self.year_front_axle_bar_and_engine):
+                return False
+            return True
+    def month_ver(self, text_list, part_name):
+        if (part_name == "front_axle_bar"):
+
+            month_char = text_list[11]
+            if (month_char not in self.month_front_axle_bar):
+                return False
+            return True
+
+        else:
+            month_char = text_list[2]
+            if (month_char not in self.month_engine):
+                return False
+            return True
+    def digit_correction(self, text_list, part_name):
+        corrected_serial_number = []
+        if (part_name == "front_axle_bar"):
+
+            serial_number = text_list[12:]
+            for ind, elem in enumerate(serial_number):
+                if(elem == "O" or elem == "o"):
+                    corrected_serial_number.append("0")
+                elif(elem == "?" or elem == "T"):
+                    corrected_serial_number.append("7")
+                elif(elem == "U"):
+                    corrected_serial_number.append("4")
+                elif(elem == "I" or elem == "i"):
+                    corrected_serial_number.append("1")
+                else:
+                    corrected_serial_number.append(elem)
+        else:
+
+            serial_number = text_list[7:]
+            for ind, elem in enumerate(serial_number):
+                if(elem == "O" or elem == "o"):
+                    corrected_serial_number.append("0")
+                elif(elem == "?" or elem == "T"):
+                    corrected_serial_number.append("7")
+                elif(elem == "U"):
+                    corrected_serial_number.append("4")
+                elif(elem == "I" or elem == "i"):
+                    corrected_serial_number.append("1")
+                else:
+                    corrected_serial_number.append(elem)
+
+        return corrected_serial_number
+
+    def defining_actual_text(self, text_list, part_name, fixed_verification, internal_verification, chassis_part, plant_verification, year_verification, month_verification, corrected_digit):
+        actual_text = []
+        if(part_name == "front_axle_bar"):
+            if(fixed_verification):
+                actual_text.extend(self.fixed)
+            else:
+                return "Image not clear", False
+            if(internal_verification):
+                if(chassis_part == "front axle_bar"):
+                    actual_text.extend(self.internal_front_axle_bar)
+                else:
+                    actual_text.extend(self.internal_front_axle_bar_2)
+
+            if(year_verification):
+                actual_text.append(text_list[9])
+            else:
+                return "Image not clear", False
+            if(month_verification):
+                actual_text.append(text_list[11])
+            else:
+                return "Image not clear", False
+            if(plant_verification):
+                actual_text.append("R")
+            else:
+                return "Image not clear", False
+            actual_text.extend(corrected_digit)
+            return actual_text, True
+        else:
+            if (plant_verification):
+                actual_text.append("R")
+            else:
+                return "Image not clear", False
+            if (year_verification):
+                actual_text.append(text_list[1])
+            else:
+                return "Image not clear", False
+
+            if (month_verification):
+                actual_text.append(text_list[2])
+            else:
+                return "Image not clear", False
+
+            if (internal_verification):
+
+                actual_text.extend(self.internal_engine)
+
+
+            if (fixed_verification):
+                pass
+            else:
+                return "Image not clear", False
+
+
+
+
+
+            actual_text.extend(corrected_digit)
+            return actual_text, True
+
+
+    def _predict(self, obj):
+
+        try:
+            frame = obj["frame"]
+            text = self.paddle_ocr_predict(self.ocr,frame)
+            print("detected text is ---------------", text)
+            part_name =self.check_character(text)
+            if not part_name:
+                text="Image not Clear"
+            else:
+                text_list = []
+                for letter in text:
+                    text_list.append(letter)
+                # print(text_list)
+                fixed_verification = self.fixed_char_check(text_list, part_name)
+                internal_verification, chassis_part = self.internal_char_check(text_list, part_name)
+                # if char_verification1:
+                #     self.recognition_output_list.extend(self.fixed_and_internal_trackter)
+                # else:
+                #     text = "Image not Clear"
+
+                # if(plant_verification):
+                plant_verification = self.plant_ver(text_list, part_name)
+                year_verification = self.year_ver(text_list, part_name)
+                month_verification = self.month_ver(text_list, part_name)
+                corrected_digit = self.digit_correction(text_list, part_name)
+                redefined_text, status = self.defining_actual_text(text_list, part_name, fixed_verification, internal_verification, chassis_part, plant_verification, year_verification, month_verification, corrected_digit)
+                if(status):
+                    if(part_name == "front_axle_bar"):
+                        year = " "
+                        month = " "
+
+                        fixed_char = redefined_text[0:3]
+                        internal_char = redefined_text[3:9]
+                        year_char = redefined_text[9]
+                        plant_char = redefined_text[11]
+                        month_char = redefined_text[10]
+                        print("MONTH------------------")
+                        print(month_char)
+                        serial_number_char = redefined_text[12:]
+                        if(year_char == "N"):
+                            year = "2022"
+                        if(month_char == "H"):
+                            month = "Augest"
+                        elif(month_char == "C"):
+                            month = "March"
+                        plant = "M$M"
+                        print("****************************************************************")
+                        internal = ''.join(str(x) for x in internal_char)
+                        fixed = ''.join(str(x) for x in fixed_char)
+                        serial_number = ''.join(str(x) for x in serial_number_char)
+                        self.recognition_output = ''.join(str(x) for x in redefined_text)
+                        self.text_json["data"]["text"] = self.recognition_output
+                        self.text_json["data"]["fixed characters"] = fixed
+                        self.text_json["data"]["internal characters"] = internal
+                        self.text_json["data"]["year"] = year
+                        self.text_json["data"]["month"] = month
+                        self.text_json["data"]["plant"] = plant
+                        self.text_json["data"]["serial number"] = serial_number
+                        self.text_json["status"] = True
+                    else:
+                        year = " "
+                        month = " "
+                        # fixed_char = redefined_text[0:3]
+                        internal_char = redefined_text[3:7]
+                        year_char = redefined_text[1]
+                        plant_char = redefined_text[0]
+                        month_char = redefined_text[2]
+                        serial_number_char = redefined_text[7:]
+                        if (year_char == "N"):
+                            year = "2022"
+                        if (month_char == "F"):
+                            month = "September"
+                        plant = "M$M"
+                        internal = ''.join(str(x) for x in internal_char)
+                        fixed = " "
+                        serial_number = ''.join(str(x) for x in serial_number_char)
+
+                    self.recognition_output = ''.join(str(x) for x in redefined_text)
+                    self.text_json["data"]["text"] = self.recognition_output
+                    self.text_json["data"]["fixed characters"] = fixed
+                    self.text_json["data"]["internal characters"] = internal
+                    self.text_json["data"]["year"] = year
+                    self.text_json["data"]["month"] = month
+                    self.text_json["data"]["plant"] = plant
+                    self.text_json["data"]["serial number"] = serial_number
+                    self.text_json["status"] = True
+
+                else:
+                    self.recognition_output = "Image not clear"
+                    self.text_json["data"]["text"] = self.recognition_output
+                    self.text_json["status"] = False
+                    self.text_json["message"] = "Image is not clear"
+
+                print(self.text_json)
+
+
+            obj["frame"] = cv2.resize(
+                frame, (self.config.get("FRAME_WIDTH"), self.config.get("FRAME_HEIGHT"))
+            )
+        except Exception as e:
+            logger.exception(f"Error: {e}", exc_info=True)
+            obj["frame"] = cv2.resize(
+                obj["frame"],
+                (self.config.get("FRAME_WIDTH"), self.config.get("FRAME_HEIGHT")),
+            )
+        return obj

scripts/cement_counter3.py

+import cv2
+import base64
+import numpy as np
+from scipy.spatial import distance
+from expiringdict import ExpiringDict
+
+from edge_engine.common.logsetup import logger
+from scripts.utils.infocenter import MongoLogger
+from yolov5processor.infer import ExecuteInference
+from scripts.utils.edge_utils import get_extra_fields
+from edge_engine.ai.model.modelwraper import ModelWrapper
+from scripts.utils.centroidtracker import CentroidTracker
+from scripts.common.constants import JanusDeploymentConstants
+from scripts.utils.image_utils import draw_circles_on_frame, resize_to_64_64
+from scripts.utils.edge_utils import Utilities
+
+from collections import deque
+from scripts.utils.tracker import Tracker
+from scripts.utils.helpers import box_iou2
+from sklearn.utils.linear_assignment_ import linear_assignment
+
+
+class CementBagCounter(ModelWrapper):
+
+    def __init__(self, config, model_config, pubs, device_id):
+        super().__init__()
+        """
+        init function
+        """
+        self.config = config["config"]
+        self.device_id = device_id
+        self.rtp = pubs.rtp_write
+        self.mongo_logger = MongoLogger()
+        self.frame_skip = self.config.get('frame_skip', False)
+        model = "data/ACC_v3.pt"
+        self.yp = ExecuteInference(weight=model,
+                                   gpu=model_config.get("gpu", False),
+                                   agnostic_nms=model_config.get("agnostic_nms", True),
+                                   iou=model_config.get("iou", 0.2),
+                                   confidence=model_config.get("confidence", 0.4))
+        self.print_eu_dist = model_config.get('print_eu_dist', 200)
+        self.ct1 = CentroidTracker(maxDisappeared=5)
+        self.ct2 = CentroidTracker(maxDisappeared=5)
+        self.frame_skipping = {
+            "skip_current_frame": True,
+            "detection_value": None
+        }
+        self.count = 0
+        self.cement_bag = 0
+        self.count_suraksha = 0
+        self.count_whitecem = 0
+        self.count_gold = 0
+        self.mrp_counter = 0
+        self.initial_object_position = Utilities.get_direction(self.device_id)
+        self.tracker_list = []
+        self.max_age = 15
+        self.min_hits = 10
+        self.track_id_list = deque([str(i) for i in range(1, 50)])
+        self.prev_annotation = []
+
+        self.initial_object_position = None
+
+        self.uncounted_objects = ExpiringDict(max_len=model_config.get("uncounted_obj_length", 50),
+                                              max_age_seconds=model_config.get("uncounted_obj_age", 60))
+        self.janus_metadata = ExpiringDict(max_age_seconds=120, max_len=1)
+
+    def _pre_process(self, x):
+        """
+        Do preprocessing here, if any
+        :param x: payload
+        :return: payload
+        """
+        return x
+
+    def _post_process(self, x):
+        """
+        Apply post processing here, if any
+        :param x: payload
+        :return: payload
+        """
+        self.rtp.publish(x)  # video stream
+        return x
+
+    def send_payload(self, frame, label='CementBagDetected', bg_color="#474520", font_color="#FFFF00", alert_sound=None,
+                     message="Cement Bag Detected!"):
+        """
+        Insert event to Mongo
+        :param message:
+        :param frame:
+        :param label:
+        :param bg_color:
+        :param font_color:
+        :param alert_sound:
+        :return: None
+        """
+
+        payload = {"deviceId": self.device_id, "message": message,
+                   "frame": 'data:image/jpeg;base64,' + base64.b64encode(
+                       cv2.imencode('.jpg', frame)[1].tostring()).decode("utf-8"), "activity": label,
+                   "bg_color": bg_color, "font_color": font_color, "alert_sound": alert_sound}
+
+        self.mongo_logger.insert_attendance_event_to_mongo(payload)
+
+    def track_bags(self, tracker_obj, dets, im0, filter_name, centroid_color=(255, 0, 0)):
+        """
+        Track the bags using Centroid based tracking
+        :param dets: prediction output
+        :param tracker_obj: prediction output
+        :param filter_name: prediction output
+        :param im0: raw frame
+        :param centroid_color: color given to the centroid marking
+        :return: centroid points, frame
+        """
+
+        bags = list()
+        classes = list()
+        for det in dets:
+            if (det["class"] in filter_name):
+                bags.append(np.array(det['points']).astype("int"))
+                classes.append(det["class"])
+
+
+        objects = tracker_obj.update(bags)
+        objects.pop("frame", None)
+
+        if centroid_color is not False:
+            for (objectID, centroid) in objects.items():
+
+                if centroid['has_print']:
+                    centroid_color = (0, 255, 0)
+
+                cv2.putText(im0, str(objectID), (centroid['centroid'][0] - 10, centroid['centroid'][1] - 10),
+                            cv2.FONT_HERSHEY_SIMPLEX,
+                            1, centroid_color, 2, cv2.LINE_AA)
+                cv2.circle(im0, (centroid['centroid'][0], centroid['centroid'][1]), 8, centroid_color, -1)
+        return objects, classes, im0
+
+    def kalman_tracker(
+            self,
+            bboxs,
+            img,
+    ):
+
+        z_box = bboxs
+        x_box = []
+
+        if len(self.tracker_list) > 0:
+            for trk in self.tracker_list:
+                x_box.append(trk.box)
+
+        matched, unmatched_dets, unmatched_trks = self.assign_detections_to_trackers(x_box, z_box, iou_thrd=0.01)
+
+        # Deal with matched detections
+        if matched.size > 0:
+            for trk_idx, det_idx in matched:
+                z = z_box[det_idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.kalman_filter(z)
+                xx = tmp_trk.x_state.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                x_box[trk_idx] = xx
+                tmp_trk.box = xx
+                tmp_trk.hits += 1
+
+        # Deal with unmatched detections
+        if len(unmatched_dets) > 0:
+            for idx in unmatched_dets:
+                z = z_box[idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = Tracker()  # Create a new tracker
+                x = np.array([[z[0], 0, z[1], 0, z[2], 0, z[3], 0]]).T
+                tmp_trk.x_state = x
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                tmp_trk.id = self.track_id_list.popleft()  # assign an ID for the tracker
+
+                self.tracker_list.append(tmp_trk)
+                x_box.append(xx)
+
+        # Deal with unmatched tracks
+        if len(unmatched_trks) > 0:
+            for trk_idx in unmatched_trks:
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.no_losses += 1
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                x_box[trk_idx] = xx
+
+        # The list of tracks to be annotated
+        good_tracker_list = []
+        objects = []
+        boxs = []
+        for trk in self.tracker_list:
+            if (trk.hits >= self.min_hits) and (trk.no_losses <= self.max_age):
+                good_tracker_list.append(trk)
+                x_cv2 = trk.box
+                left, top, right, bottom = x_cv2[1], x_cv2[0], x_cv2[3], x_cv2[2]
+                centroid = [int(left + ((right - left) / 2)), bottom]
+                objects.append([int(trk.id), centroid])
+                boxs.append(x_cv2)
+
+        deleted_tracks = filter(lambda _x: _x.no_losses > self.max_age, self.tracker_list)
+
+        for trk in deleted_tracks:
+            self.track_id_list.append(trk.id)
+
+        self.tracker_list = [x for x in self.tracker_list if x.no_losses <= self.max_age]
+        print("object is ", str(objects))
+        return img, objects, boxs
+
+    @staticmethod
+    def assign_detections_to_trackers(
+            trackers,
+            detections,
+            iou_thrd=0.3,
+    ):
+        """
+        From current list of trackers and new detections, output matched detections,
+        un matched trackers, unmatched detections.
+        """
+        iou_mat = np.zeros((len(trackers), len(detections)), dtype=np.float32)
+        for t, trk in enumerate(trackers):
+            for d, det in enumerate(detections):
+                iou_mat[t, d] = box_iou2(trk, det)
+
+        matched_idx = linear_assignment(-iou_mat)
+
+        unmatched_trackers, unmatched_detections = [], []
+        for t, trk in enumerate(trackers):
+            if t not in matched_idx[:, 0]:
+                unmatched_trackers.append(t)
+
+        for d, det in enumerate(detections):
+            if d not in matched_idx[:, 1]:
+                unmatched_detections.append(d)
+
+        matches = []
+
+        for m in matched_idx:
+            if iou_mat[m[0], m[1]] < iou_thrd:
+                unmatched_trackers.append(m[0])
+                unmatched_detections.append(m[1])
+            else:
+                matches.append(m.reshape(1, 2))
+
+        if len(matches) == 0:
+            matches = np.empty((0, 2), dtype=int)
+        else:
+            matches = np.concatenate(matches, axis=0)
+
+        return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
+
+
+
+
+    def get_line_coordinates(self):
+        """
+        Get the line coordinates from the deployment JSON
+        """
+        if not self.janus_metadata.get('metadata'):
+            self.janus_metadata['metadata'] = get_extra_fields(self.device_id)
+
+        _coordinates = [self.janus_metadata['metadata'].get(coordinate_key) for coordinate_key in
+                        JanusDeploymentConstants.LINE_COORDINATES]
+        _alignment = self.janus_metadata['metadata'].get(JanusDeploymentConstants.ALIGNMENT_KEY)
+        return _alignment, _coordinates
+
+    def line_point_position(self, point):
+        """
+        Get the position of point w.r.t. the line
+        :param point: point to be compared
+        :return: boolean
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+        assert len(point) == 2, "Point variable is invalid"
+
+        _slope = (line_coordinates[3] - line_coordinates[1]) / (line_coordinates[2] - line_coordinates[0])
+        _point_equation_value = point[1] - line_coordinates[1] - _slope * (point[0] - line_coordinates[0])
+        if _point_equation_value > 0:
+            return True
+        else:
+            return False
+
+    def validate_point_position(self, point):
+        """
+        Validate the position of the point w.r.t. the line
+        :param point: centroid
+        :return: bool
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert _alignment in [JanusDeploymentConstants.VERTICAL, JanusDeploymentConstants.HORIZONTAL], \
+            "Invalid alignment variable"
+        if _alignment == JanusDeploymentConstants.VERTICAL:
+            line_y2 = line_coordinates[3]
+            line_y1 = line_coordinates[1]
+            if line_y1 < point[1] < line_y2 or line_y2 < point[1] < line_y1:
+                return True
+            else:
+                return False
+        else:
+            line_x2 = line_coordinates[2]
+            line_x1 = line_coordinates[0]
+            if line_x1 < point[0] < line_x2 or line_x2 < point[0] < line_x1:
+                return True
+            else:
+                return False
+
+    def update_bag_count(self, frame, detection_objects, classes):
+        """
+        Maintains the bag counts
+        :param frame: image
+        :param detection_objects: detection object having object id and centroids
+        """
+        for class_name, (objectID, centroid) in zip(classes, detection_objects.items()):
+
+            if self.validate_point_position(centroid['centroid']):
+                logger.debug("centroid detected")
+
+                if not isinstance(self.initial_object_position, bool):
+                    logger.debug("Initializing the initial object position")
+                    self.initial_object_position = self.line_point_position(point=centroid['centroid'])
+                    Utilities.set_direction(self.device_id, self.initial_object_position)
+                    #self.initial_object_position = True
+                    logger.debug(self.initial_object_position)
+
+                _point_position = self.line_point_position(point=centroid['centroid'])
+                logger.debug("object ID is : ", str(objectID))
+                logger.debug(self.uncounted_objects)
+
+                # Check point in the same side as the initial object
+                if _point_position == self.initial_object_position:
+                    logger.debug("same side only")
+                    # Check the object is not already counted
+                    if objectID not in self.uncounted_objects:
+                        self.uncounted_objects[objectID] = centroid['centroid']
+                    frame = draw_circles_on_frame(frame, centroid['centroid'], radius=10, color=(0, 0, 255),
+                                                  thickness=-1)
+
+                elif objectID in self.uncounted_objects:
+                    logger.debug("different side")
+                    self.uncounted_objects.pop(objectID, None)
+                    if (class_name == "acc_gold"):
+                        self.count_gold += 1
+                        logger.debug(self.count_gold)
+                    elif (class_name == "acc_suraksha_plus"):
+                        self.count_suraksha += 1
+                        logger.debug(self.count_suraksha)
+                    elif (class_name == "ambuja_whitecem"):
+                        self.count_whitecem += 1
+                        logger.debug(self.count_whitecem)
+                    frame = draw_circles_on_frame(frame, centroid['centroid'], radius=10, color=(0, 255, 0),
+                                                  thickness=-1)
+                    if centroid['has_print']:
+                        self.send_payload(resize_to_64_64(frame=frame), message='Print Detected!')
+                        logger.info(f"Count: {self.count}, Print Found: True")
+                    else:
+                        self.send_payload(resize_to_64_64(frame=frame), message='Print Missing!')
+                        logger.info(f"Count: {self.count}, Print Found: False")
+                else:
+                    frame = draw_circles_on_frame(frame, centroid['centroid'], radius=10, color=(0, 255, 0),
+                                                  thickness=-1)
+        count_text_gold = "ACC_GOLD: " + str(self.count_gold)
+        count_text_suraksha = "ACC_SURAKSHA_P_PLUS: " + str(self.count_suraksha)
+        count_text_whitecem = "PPC_WHITE: " + str(self.count_whitecem)
+        cv2.putText(frame, count_text_gold, (1300, 200), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+                    cv2.LINE_AA)
+        cv2.putText(frame, count_text_suraksha, (1300, 400), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+                    cv2.LINE_AA)
+        cv2.putText(frame, count_text_whitecem, (1300, 600), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+                    cv2.LINE_AA)
+        return frame
+
+    def draw_line_over_image(self, frame, color=(255, 255, 255)):
+        """
+        Draws line over the counting line
+        :param frame: frame for
+        :param color:
+        :return:
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+
+        # return cv2.line(frame, (line_coordinates[0], line_coordinates[1]), (line_coordinates[2], line_coordinates[3]),
+        #                 color, 3)
+
+        self.drawline(frame, (line_coordinates[0], line_coordinates[1]), (line_coordinates[2],
+                                                                          line_coordinates[3]), color, thickness=3)
+        return frame
+
+    @staticmethod
+    def drawline(img, pt1, pt2, color, thickness=1, style='dotted', gap=20):
+        dist = ((pt1[0] - pt2[0]) ** 2 + (pt1[1] - pt2[1]) ** 2) ** .5
+        pts = []
+        for i in np.arange(0, dist, gap):
+            r = i / dist
+            x = int((pt1[0] * (1 - r) + pt2[0] * r) + .5)
+            y = int((pt1[1] * (1 - r) + pt2[1] * r) + .5)
+            p = (x, y)
+            pts.append(p)
+
+        if style == 'dotted':
+            for p in pts:
+                cv2.circle(img, p, thickness, color, -1)
+        else:
+            s = pts[0]
+            e = pts[0]
+            i = 0
+            for p in pts:
+                s = e
+                e = p
+                if i % 2 == 1:
+                    cv2.line(img, s, e, color, thickness)
+                i += 1
+
+    def distances(self, objs1, objs2):
+        for key1, val1 in objs1.items():
+            for key2, val2 in objs2.items():
+                dst = distance.euclidean(val1['centroid'], val2['centroid'])
+                if objs1[key1]['has_print']:
+                    self.mrp_counter += 1
+                    if(self.mrp_counter >= 5):
+                        #STOP THE RELAY
+                        pass
+                    continue
+                elif dst < self.print_eu_dist:
+                    objs1[key1]['has_print'] = True
+                    self.mrp_counter = 0
+
+    # def inference(
+    #         self,
+    #         frame,
+    #         classes,
+    #
+    # ):
+    #     dets = self.yp.predict(frame)
+    #     class_name = list()
+    #     bboxs = []
+    #
+    #     if dets:
+    #         for i in dets:
+    #             if(i["class"] in classes):
+    #                 class_name.append(i["class"])
+    #             bboxs.append([i["points"][1], i["points"][0], i["points"][3], i["points"][2]])
+    #
+    #     print("#######")
+    #     print(bboxs)
+    #     #frame = cv2.rectangle(frame, (bboxs[0][0], bboxs[0][1]), (bboxs[0][2], bboxs[0][3]),(255, 255, 0) , 2)
+    #     return bboxs, frame, dets, class_name
+
+
+    def inference(
+            self,
+            frame,
+    ):
+        dets = self.yp.predict(frame)
+        bboxs = []
+        if dets:
+            for i in dets:
+                bboxs.append([i["points"][1], i["points"][0], i["points"][3], i["points"][2]])
+        return bboxs, frame, dets
+
+    def _predict(self, obj):
+        class_list = ["acc_gold", "acc_suraksha_plus", "ambuja_buildcem"]
+        try:
+            frame = obj['frame']
+
+            if self.frame_skip:
+                if not self.frame_skipping["skip_current_frame"]:
+                    dets = self.yp.predict(frame)
+                    self.frame_skipping["detection_value"] = dets
+                    self.frame_skipping["skip_current_frame"] = True
+                else:
+                    dets = self.frame_skipping["detection_value"]
+                    self.frame_skipping["skip_current_frame"] = False
+            else:
+
+                dets, frame, _dets = self.inference(frame)
+                print("PRINTING INFERENCE FUNCTION OUTPUT")
+                print(dets)
+                print(_dets)
+                #print(class_name)
+                #if dets:
+                frame, objects, boxs = self.kalman_tracker(dets, frame)
+                print("PRINTING KALMAN OUTPUTS")
+                print(objects)
+                print(boxs)
+
+                dets = self.yp.predict(frame)
+
+            frame = self.draw_line_over_image(frame)
+            # if [True for e in dets if e['class'] == 'cement_bag']:
+            #class_list = ["acc_gold", "acc_suraksha_plus", "ambuja_whitecem"]
+            mrp = ["mrp"]
+            objects,classes_cement, frame = self.track_bags(self.ct1, dets, frame, class_list)
+            _,classes, frame = self.track_bags(self.ct2, dets, frame, mrp)
+            frame = self.update_bag_count(frame=frame, detection_objects=objects, classes = classes_cement)
+            cv2.imshow("output is ", cv2.resize(frame, (900, 600)))
+            cv2.waitKey(1)
+            self.distances(objects, _)
+            logger.debug("self.uncounted_objects --> {}".format(self.uncounted_objects))
+            # for each in dets:
+            #     color = (255, 255, 0)
+            #     class_n = "Cement Bag"
+            #
+            #     if each['class'] == 'label':
+            #         color = (0, 255, 0)
+            #         class_n = "Printing Detected!"
+            #     cv2.rectangle(frame, (each['points'][0], each['points'][1]), (each['points'][2], each['points'][3]),
+            #                   color, 2)
+            #     cv2.putText(frame, class_n, (each['points'][2], each['points'][1]), cv2.FONT_HERSHEY_SIMPLEX,
+            #                 1, color, 2, cv2.LINE_AA)
+
+            obj['frame'] = cv2.resize(frame, (self.config.get('FRAME_WIDTH'), self.config.
+                                              get('FRAME_HEIGHT')))
+        except Exception as e:
+            logger.exception(f"Error: {e}", exc_info=True)
+            obj['frame'] = cv2.resize(obj['frame'], (self.config.get('FRAME_WIDTH'), self.config.get('FRAME_HEIGHT')))
+
+        return obj

scripts/cement_counter_for_acc_final - Copy.py

+import cv2
+import base64
+import numpy as np
+from scipy.spatial import distance
+from expiringdict import ExpiringDict
+
+from edge_engine.common.logsetup import logger
+from scripts.utils.infocenter import MongoLogger
+from yolov5processor.infer import ExecuteInference
+from scripts.utils.edge_utils import get_extra_fields
+from edge_engine.ai.model.modelwraper import ModelWrapper
+from scripts.utils.centroidtracker import CentroidTracker
+from scripts.common.constants import JanusDeploymentConstants
+from scripts.utils.image_utils import draw_circles_on_frame, resize_to_64_64
+
+import cv2
+import base64
+import datetime
+import numpy as np
+
+from collections import deque
+from expiringdict import ExpiringDict
+from sklearn.utils.linear_assignment_ import linear_assignment
+
+from edge_engine.common.logsetup import logger
+from edge_engine.ai.model.modelwraper import ModelWrapper
+
+from scripts.utils.tracker import Tracker
+from scripts.utils.helpers import box_iou2
+from scripts.utils.edge_utils import Utilities
+from scripts.utils.infocenter import MongoLogger
+from scripts.utils.model_tracker import ModelCountTracker
+from scripts.common.constants import JanusDeploymentConstants
+
+from yolov5processor.infer import ExecuteInference
+
+
+class CementBagCounter(ModelWrapper):
+
+    def __init__(self, config, model_config, pubs, device_id):
+        super().__init__()
+        """
+        init function
+        """
+        self.config = config["config"]
+        self.device_id = device_id
+        self.rtp = pubs.rtp_write
+        self.mongo_logger = MongoLogger()
+        self.frame_skip = self.config.get('frame_skip', False)
+        model = "data/ACC_v3.pt"
+        self.yp = ExecuteInference(weight=model,
+                                   gpu=model_config.get("gpu", False),
+                                   agnostic_nms=model_config.get("agnostic_nms", True),
+                                   iou=model_config.get("iou", 0.2),
+                                   confidence=model_config.get("confidence", 0.4))
+        self.print_eu_dist = model_config.get('print_eu_dist', 200)
+        self.ct1 = CentroidTracker(maxDisappeared=5)
+        self.ct2 = CentroidTracker(maxDisappeared=5)
+        self.frame_skipping = {
+            "skip_current_frame": True,
+            "detection_value": None
+        }
+        self.count = 0
+        self.cement_bag = 0
+        self.count_suraksha = 0
+        self.count_whitecem = 0
+        self.count_gold = 0
+        self.tracker_list = []
+        self.max_age = 3
+        self.min_hits = 0
+        self.track_id_list = deque([str(i) for i in range(1, 50)])
+        self.prev_annotation = []
+
+
+        self.initial_object_position = None
+
+        self.uncounted_objects = ExpiringDict(max_len=model_config.get("uncounted_obj_length", 50),
+                                              max_age_seconds=model_config.get("uncounted_obj_age", 60))
+        self.janus_metadata = ExpiringDict(max_age_seconds=120, max_len=1)
+
+    def _pre_process(self, x):
+        """
+        Do preprocessing here, if any
+        :param x: payload
+        :return: payload
+        """
+        return x
+
+    def _post_process(self, x):
+        """
+        Apply post processing here, if any
+        :param x: payload
+        :return: payload
+        """
+        self.rtp.publish(x)  # video stream
+        return x
+
+    def send_payload(self, frame, label='CementBagDetected', bg_color="#474520", font_color="#FFFF00", alert_sound=None,
+                     message="Cement Bag Detected!"):
+        """
+        Insert event to Mongo
+        :param message:
+        :param frame:
+        :param label:
+        :param bg_color:
+        :param font_color:
+        :param alert_sound:
+        :return: None
+        """
+
+        payload = {"deviceId": self.device_id, "message": message,
+                   "frame": 'data:image/jpeg;base64,' + base64.b64encode(
+                       cv2.imencode('.jpg', frame)[1].tostring()).decode("utf-8"), "activity": label,
+                   "bg_color": bg_color, "font_color": font_color, "alert_sound": alert_sound}
+
+        self.mongo_logger.insert_attendance_event_to_mongo(payload)
+
+    def kalman_tracker(
+            self,
+            bboxs,
+            img,
+    ):
+
+        z_box = bboxs
+        x_box = []
+
+        if len(self.tracker_list) > 0:
+            for trk in self.tracker_list:
+                x_box.append(trk.box)
+
+        matched, unmatched_dets, unmatched_trks = self.assign_detections_to_trackers(x_box, z_box, iou_thrd=0.03)
+
+        # Deal with matched detections
+        if matched.size > 0:
+            for trk_idx, det_idx in matched:
+                z = z_box[det_idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.kalman_filter(z)
+                xx = tmp_trk.x_state.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                x_box[trk_idx] = xx
+                tmp_trk.box = xx
+                tmp_trk.hits += 1
+
+        # Deal with unmatched detections
+        if len(unmatched_dets) > 0:
+            for idx in unmatched_dets:
+                z = z_box[idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = Tracker()  # Create a new tracker
+                x = np.array([[z[0], 0, z[1], 0, z[2], 0, z[3], 0]]).T
+                tmp_trk.x_state = x
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                tmp_trk.id = self.track_id_list.popleft()  # assign an ID for the tracker
+
+                self.tracker_list.append(tmp_trk)
+                x_box.append(xx)
+
+        # Deal with unmatched tracks
+        if len(unmatched_trks) > 0:
+            for trk_idx in unmatched_trks:
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.no_losses += 1
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                x_box[trk_idx] = xx
+
+        # The list of tracks to be annotated
+        good_tracker_list = []
+        objects = []
+        boxs = []
+        for trk in self.tracker_list:
+            if (trk.hits >= self.min_hits) and (trk.no_losses <= self.max_age):
+                good_tracker_list.append(trk)
+                x_cv2 = trk.box
+                left, top, right, bottom = x_cv2[1], x_cv2[0], x_cv2[3], x_cv2[2]
+                centroid = [int(left + ((right - left) / 2)), bottom]
+                objects.append([int(trk.id), centroid])
+                boxs.append(x_cv2)
+
+        deleted_tracks = filter(lambda _x: _x.no_losses > self.max_age, self.tracker_list)
+
+        for trk in deleted_tracks:
+            self.track_id_list.append(trk.id)
+
+        self.tracker_list = [x for x in self.tracker_list if x.no_losses <= self.max_age]
+       # print("object is ", str(objects))
+
+        return img, objects, boxs
+
+    @staticmethod
+    def assign_detections_to_trackers(
+            trackers,
+            detections,
+            iou_thrd=0.3,
+    ):
+        """
+        From current list of trackers and new detections, output matched detections,
+        un matched trackers, unmatched detections.
+        """
+        iou_mat = np.zeros((len(trackers), len(detections)), dtype=np.float32)
+        for t, trk in enumerate(trackers):
+            for d, det in enumerate(detections):
+                iou_mat[t, d] = box_iou2(trk, det)
+
+        matched_idx = linear_assignment(-iou_mat)
+
+        unmatched_trackers, unmatched_detections = [], []
+        for t, trk in enumerate(trackers):
+            if t not in matched_idx[:, 0]:
+                unmatched_trackers.append(t)
+
+        for d, det in enumerate(detections):
+            if d not in matched_idx[:, 1]:
+                unmatched_detections.append(d)
+
+        matches = []
+
+        for m in matched_idx:
+            if iou_mat[m[0], m[1]] < iou_thrd:
+                unmatched_trackers.append(m[0])
+                unmatched_detections.append(m[1])
+            else:
+                matches.append(m.reshape(1, 2))
+
+        if len(matches) == 0:
+            matches = np.empty((0, 2), dtype=int)
+        else:
+            matches = np.concatenate(matches, axis=0)
+
+        return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
+
+
+
+    def get_line_coordinates(self):
+        """
+        Get the line coordinates from the deployment JSON
+        """
+        if not self.janus_metadata.get('metadata'):
+            self.janus_metadata['metadata'] = get_extra_fields(self.device_id)
+
+        _coordinates = [self.janus_metadata['metadata'].get(coordinate_key) for coordinate_key in
+                        JanusDeploymentConstants.LINE_COORDINATES]
+        _alignment = self.janus_metadata['metadata'].get(JanusDeploymentConstants.ALIGNMENT_KEY)\
+        # _coordinates = [550, 200, 555, 1100]
+        #
+        # _alignment = "vertical"
+        return _alignment, _coordinates
+
+    def line_point_position(self, point):
+        """
+        Get the position of point w.r.t. the line
+        :param point: point to be compared
+        :return: boolean
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+        assert len(point) == 2, "Point variable is invalid"
+
+        _slope = (line_coordinates[3] - line_coordinates[1]) / (line_coordinates[2] - line_coordinates[0])
+        _point_equation_value = point[1] - line_coordinates[1] - _slope * (point[0] - line_coordinates[0])
+        if _point_equation_value > 0:
+            return True
+        else:
+            return False
+
+    def validate_point_position(self, point):
+        """
+        Validate the position of the point w.r.t. the line
+        :param point: centroid
+        :return: bool
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert _alignment in [JanusDeploymentConstants.VERTICAL, JanusDeploymentConstants.HORIZONTAL], \
+            "Invalid alignment variable"
+        if _alignment == JanusDeploymentConstants.VERTICAL:
+        # _alignment, line_coordinates = self.get_line_coordinates()
+        # assert _alignment in ["horizontal", "vertical"], \
+        #     "Invalid alignment variable"
+        # print(point)
+        # if _alignment == "vertical":
+            line_y2 = line_coordinates[3]
+            line_y1 = line_coordinates[1]
+            if line_y1 < point[1] < line_y2 or line_y2 < point[1] < line_y1:
+                return True
+            else:
+                return False
+        else:
+            line_x2 = line_coordinates[2]
+            line_x1 = line_coordinates[0]
+            if line_x1 < point[0] < line_x2 or line_x2 < point[0] < line_x1:
+
+                return True
+            else:
+                return False
+
+    def update_bag_count(self, frame, detection_objects, class_name, detections):
+        """
+        Maintains the bag counts
+        :param frame: image
+        :param detection_objects: detection object having object id and centroids
+        """
+        #for class_name, (objectID, centroid) in zip(classes, detection_objects):
+        for (object_id, det) in zip(detection_objects, detections):
+            centroid = object_id[1]
+            object_id = object_id[0]
+            logger.debug(detections)
+            #print(object_id)
+            frame = draw_circles_on_frame(frame, centroid, radius=10, color=(0, 0, 255),
+                                          thickness=-1)
+            if self.validate_point_position(centroid):
+                logger.debug("centroid detected")
+                #if self.validate_point_position(centroid):
+
+                # # if not isinstance(self.count, int):
+                # #     logger.debug("Initializing the count variable")
+                # print("again entering")
+                # # Initializing the bag count
+                # if (class_name == "acc_gold"):
+                #     if not isinstance(self.count_gold, int):
+                #         logger.debug("Initializing the count variable")
+                #         self.count_gold = 0
+                # elif (class_name == "acc_suraksha"):
+                #     if not isinstance(self.count_suraksha, int):
+                #         logger.debug("Initializing the count variable")
+                #         self.count_suraksha = 0
+                # elif (class_name == "acc_buildcem"):
+                #     if not isinstance(self.count_whitecem, int):
+                #         logger.debug("Initializing the count variable")
+                #         self.count_whitecem = 0
+
+                if not isinstance(self.initial_object_position, bool):
+                    logger.debug("Initializing the initial object position")
+                    #self.initial_object_position = self.line_point_position(point=centroid)
+                    self.initial_object_position = True
+                    logger.debug(self.initial_object_position)
+
+                _point_position = self.line_point_position(point=centroid)
+                #print("object ID is : ", str(objectID))
+                logger.debug(self.uncounted_objects)
+
+                # Check point in the same side as the initial object
+                if _point_position == self.initial_object_position:
+                    logger.debug("same side only")
+                    #print(class_name)
+                    # Check the object is not already counted
+                    if object_id not in self.uncounted_objects:
+                        self.uncounted_objects[object_id] = centroid
+
+
+                elif object_id in self.uncounted_objects:
+                    self.uncounted_objects.pop(object_id, None)
+                    if ("acc_gold" in class_name):
+                        self.count_gold += 1
+                        mrp_result = self.distances(detections)
+                        if mrp_result:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='ACC GOLD Bag Detected: Print Detected!')
+                            logger.info(f"Count: {self.count_gold}, Print Found: True")
+                        else:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='ACC GOLD Bag Detected: Print Missing!')
+                            logger.info(f"Count: {self.count_gold}, Print Found: False")
+
+
+
+                    elif ("acc_suraksha_plus" in class_name):
+                        self.count_suraksha += 1
+                        logger.debug(self.count_suraksha)
+                        mrp_result = self.distances(detections)
+                        if mrp_result:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='ACC SURAKSHA PLUS Bag Detected: Print Detected!')
+                            logger.info(f"Count: {self.count_suraksha}, Print Found: True")
+                        else:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='ACC SURAKSHA PLUS Bag Detected: Print Missing!')
+                            logger.info(f"Count: {self.count_suraksha}, Print Found: False")
+
+                    elif ("ambuja_whitecem" in class_name):
+                        self.count_whitecem += 1
+                        mrp_result = self.distances(detections)
+                        if mrp_result:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='PPC White Bag Detected: Print Detected!')
+                            logger.info(f"Count: {self.count_whitecem}, Print Found: True")
+                        else:
+                            self.send_payload(resize_to_64_64(frame=frame),
+                                              message='PPC White Bag Detected: Print Missing!')
+                            logger.info(f"Count: {self.count_whitecem}, Print Found: False")
+
+                    frame = draw_circles_on_frame(frame, centroid['centroid'], radius=10, color=(0, 255, 0),
+                                                  thickness=-1)
+                    if centroid['has_print']:
+                        self.send_payload(resize_to_64_64(frame=frame), message='Print Detected!')
+                        logger.info(f"Count: {self.count}, Print Found: True")
+                    else:
+                        self.send_payload(resize_to_64_64(frame=frame), message='Print Missing!')
+                        logger.info(f"Count: {self.count}, Print Found: False")
+                else:
+                    frame = draw_circles_on_frame(frame, centroid['centroid'], radius=10, color=(0, 255, 0),
+                                                  thickness=-1)
+
+        # count_text_gold = "ACC_GOLD: " + str(self.count_gold)
+        # count_text_suraksha = "ACC_SURAKSHA_PLUS: " + str(self.count_suraksha)
+        # count_text_whitecem = "ACC_WHITE_CEM: " + str(self.count_whitecem)
+        # cv2.putText(frame, count_text_gold, (1300, 200), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_suraksha, (1300, 400), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_whitecem, (1300, 600), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        return frame
+
+    def draw_line_over_image(self, frame, color=(255, 255, 255)):
+        """
+        Draws line over the counting line
+        :param frame: frame for
+        :param color:
+        :return:
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+
+        # return cv2.line(frame, (line_coordinates[0], line_coordinates[1]), (line_coordinates[2], line_coordinates[3]),
+        #                 color, 3)
+
+        self.drawline(frame, (line_coordinates[0], line_coordinates[1]), (line_coordinates[2],
+                                                                          line_coordinates[3]), color, thickness=3)
+        return frame
+
+    @staticmethod
+    def drawline(img, pt1, pt2, color, thickness=1, style='dotted', gap=20):
+        dist = ((pt1[0] - pt2[0]) ** 2 + (pt1[1] - pt2[1]) ** 2) ** .5
+        pts = []
+        for i in np.arange(0, dist, gap):
+            r = i / dist
+            x = int((pt1[0] * (1 - r) + pt2[0] * r) + .5)
+            y = int((pt1[1] * (1 - r) + pt2[1] * r) + .5)
+            p = (x, y)
+            pts.append(p)
+
+        if style == 'dotted':
+            for p in pts:
+                cv2.circle(img, p, thickness, color, -1)
+        else:
+            s = pts[0]
+            e = pts[0]
+            i = 0
+            for p in pts:
+                s = e
+                e = p
+                if i % 2 == 1:
+                    cv2.line(img, s, e, color, thickness)
+                i += 1
+
+    def distances(self, detections):
+        mrp_cord = list()
+        cem_bag_cord = list()
+        for det in detections:
+            if(det["class"] == "mrp"):
+                mrp_cord.append(det["points"])
+            else:
+                cem_bag_cord.append(det["points"])
+        for c_cord in cem_bag_cord:
+            for m_cord in mrp_cord:
+
+                if (m_cord[0] > c_cord[0] and m_cord[0] < c_cord[2] and
+                        m_cord[1] > c_cord[1] and m_cord[1] < c_cord[3]):
+                    logger.debug("print is detected")
+                    #cv2.waitKey(0)
+                    return True
+                else:
+                    return False
+
+
+    def inference(
+            self,
+            frame,
+            classes,
+
+    ):
+        dets = self.yp.predict(frame)
+        class_name = list()
+        bboxs = []
+
+        if dets:
+            for i in dets:
+                if(i["class"] in classes):
+                    class_name.append(i["class"])
+                    #cv2.rectangle(frame, (i["points"][0], i["points"][1]), (i["points"][2], i["points"][3]), (255, 255, 0), 2)
+                    bboxs.append([i["points"][1], i["points"][0], i["points"][3], i["points"][2]])
+
+#        frame = cv2.rectangle(frame, (bboxs[0][0], bboxs[0][1]), (bboxs[0][2], bboxs[0][3]),(255, 255, 0) , 2)
+        return bboxs, frame, dets, class_name
+
+    def _predict(self, obj):
+        class_list = ["acc_gold", "acc_suraksha_plus", "ambuja_whitecem"]
+        mrp = ["mrp"]
+        try:
+            frame = obj['frame']
+
+            if self.frame_skip:
+                if not self.frame_skipping["skip_current_frame"]:
+                    dets = self.yp.predict(frame)
+                    self.frame_skipping["detection_value"] = dets
+                    self.frame_skipping["skip_current_frame"] = True
+                else:
+                    dets = self.frame_skipping["detection_value"]
+                    self.frame_skipping["skip_current_frame"] = False
+            else:
+                dets, frame, _dets, class_name = self.inference(frame, class_list)
+
+
+                #dets_mrp, frame_mrp, _dets_mrp, class_name_mrp = self.inference(frame, mrp)
+
+            frame = self.draw_line_over_image(frame)
+            # if [True for e in dets if e['class'] == 'cement_bag']:
+
+
+            #if dets:
+            frame, objects, boxs = self.kalman_tracker(dets, frame)
+            print("PRINTING KALMAN OUTPUT")
+            print(objects)
+            print(boxs)
+            for box in boxs:
+                cv2.rectangle(frame, (box[1], box[0]), (box[3], box[2]), (255, 0, 0), 2)
+
+            #objects,classes_cement, frame = self.track_bags(self.ct1, dets, frame, class_list)
+            #_,classes, frame = self.track_bags(self.ct2, _dets, frame, mrp)
+            #frame, _, box_mrp = self.kalman_tracker(dets_mrp, frame)
+            frame = self.update_bag_count(frame=frame, detection_objects=objects, class_name = class_name, detections = _dets)
+            # cv2.imshow("output is ", cv2.resize(frame, (900, 600)))
+            # cv2.waitKey(1)
+            # print("******")
+            # print(objects)
+            # print(_)
+
+            # self.distances(objects, _)
+            logger.debug("self.uncounted_objects --> {}".format(self.uncounted_objects))
+            # for each in dets:
+            #     color = (255, 255, 0)
+            #     class_n = "Cement Bag"
+            #
+            #     if each['class'] == 'label':
+            #         color = (0, 255, 0)
+            #         class_n = "Printing Detected!"
+            #     cv2.rectangle(frame, (each['points'][0], each['points'][1]), (each['points'][2], each['points'][3]),
+            #                   color, 2)
+            #     cv2.putText(frame, class_n, (each['points'][2], each['points'][1]), cv2.FONT_HERSHEY_SIMPLEX,
+            #                 1, color, 2, cv2.LINE_AA)
+
+            obj['frame'] = cv2.resize(frame, (self.config.get('FRAME_WIDTH'), self.config.
+                                              get('FRAME_HEIGHT')))
+        except Exception as e:
+            logger.exception(f"Error: {e}", exc_info=True)
+            obj['frame'] = cv2.resize(obj['frame'], (self.config.get('FRAME_WIDTH'), self.config.get('FRAME_HEIGHT')))
+
+        return obj

scripts/cement_counter_jithu_padddle_ocr.py

+import cv2
+import json
+import base64
+import numpy as np
+from scipy.spatial import distance
+from expiringdict import ExpiringDict
+import time
+from edge_engine.common.logsetup import logger
+from scripts.utils.infocenter import MongoLogger
+# from yolov5processor.infer import ExecuteInference
+from scripts.utils.edge_utils import get_extra_fields
+from edge_engine.ai.model.modelwraper import ModelWrapper
+from scripts.utils.centroidtracker import CentroidTracker
+from scripts.common.constants import JanusDeploymentConstants
+from scripts.utils.image_utils import draw_circles_on_frame, resize_to_64_64
+from pymongo import MongoClient
+from scripts.common.config import MONGO_URI
+from uuid import uuid4
+import cv2
+import base64
+import datetime
+import numpy as np
+import imutils
+from collections import deque
+from expiringdict import ExpiringDict
+from sklearn.utils.linear_assignment_ import linear_assignment
+
+from edge_engine.common.logsetup import logger
+from edge_engine.ai.model.modelwraper import ModelWrapper
+
+from scripts.utils.tracker import Tracker
+from scripts.utils.helpers import box_iou2
+from scripts.utils.edge_utils import Utilities
+from scripts.utils.infocenter import MongoLogger
+from scripts.utils.model_tracker import ModelCountTracker
+from scripts.common.constants import JanusDeploymentConstants
+
+# TRT Additions start
+# from yolov5processor.infer import ExecuteInference
+# from scripts.utils.yolov5_trt import YoloV5TRT
+# TRT Additions stop
+
+from scripts.utils.relay_util import RelayHandler
+from paddleocr import PaddleOCR
+
+
+class CementBagCounter(ModelWrapper):
+
+    def __init__(self, config, model_config, pubs, device_id):
+        super().__init__()
+        """
+        init function
+        """
+        self.config = config["config"]
+        self.device_id = device_id
+        self.rtp = pubs.rtp_write
+        self.mongo_logger = MongoLogger()
+        self.frame_skip = self.config.get('frame_skip', False)
+
+        # TRT Additions start
+
+        # model = "data/acc_v6.pt"
+        # self.yp = ExecuteInference(weight=model,
+        #                            gpu=model_config.get("gpu", False),
+        #                            agnostic_nms=model_config.get("agnostic_nms", True),
+        #                            iou=model_config.get("iou", 0.2),
+        #                            confidence=model_config.get("confidence", 0.4))
+        engine_file_path = "data/acc_v14.engine"
+        # with open("/home/ilens/container_weights/classes.json", 'r') as f:
+        #     self.classes = json.loads(f.read())
+        #     self.classes = {int(k): v for k, v in self.classes.items()}
+        self.classes = {0: 'ambuja_plus', 1: 'acc_gold', 2: 'acc_suraksha_power_plus', 3: 'ambuja_buildcem', 4: 'mrp', 5: 'acc_suraksha_power', 6: 'acc_nfr', 7: 'acc_concrete_plus'}
+        # self.yolo_v5_wrapper = YoloV5TRT(engine_file_path, model_config.get('conf_thresh', 0.5),
+        #                                                  model_config.get('iou_thresh', 0.4))
+
+        # TRT Additions stop
+
+        # self.print_eu_dist = model_config.get('print_eu_dist', 200)
+        self.ct1 = CentroidTracker(maxDisappeared=5)
+        self.ct2 = CentroidTracker(maxDisappeared=5)
+
+        self.count = 0
+        self.cement_bag = 0
+        self.count_suraksha = 0
+        self.count_whitecem = 0
+        self.count_gold = 0
+        self.tracker_list = []
+        self.max_age = 3
+        self.min_hits = 0
+        self.track_id_list = deque([str(i) for i in range(1, 50)])
+        self.prev_annotation = []
+        self.mrp_counter = 0
+        self.count_nfr = 0
+        self.count_suraksha_power = 0
+        self.count_concrete_plus = 0
+        self.count_ambuja_plus = 0
+        # self.prev_class_name = None
+
+        self.initial_object_position = None
+
+        self.uncounted_objects = ExpiringDict(max_len=model_config.get("uncounted_obj_length", 50),
+                                              max_age_seconds=model_config.get("uncounted_obj_age", 60))
+        self.janus_metadata = ExpiringDict(max_age_seconds=120, max_len=1)
+        self.mongo_alarm_coll = MongoClient(MONGO_URI)['ilens_events']['triggered_alarms']
+        self.camera_details = self.mongo_logger.get_camera_details(self.device_id)
+        self.black_white_ratio_dict = {'ambuja_plus': 1.2, 'acc_gold': 1.2, 'acc_suraksha_power_plus': 1.2,
+                                  'ambuja_buildcem': 1.2, 'acc_suraksha_power': 1.2, 'acc_nfr': 1.2,
+                                  'acc_concrete_plus': 1.2}
+    def paddle_ocr_load_model(self):
+        ocr = PaddleOCR(
+            lang="en",
+            # det_db_thresh=0.1,
+            # det_db_box_thresh=0.1,
+            # use_mp=True,
+            # total_process_num=process_count,
+            use_angle_cls=True,
+            cls_model_dir="paddleocr/model/ch_ppocr_mobile_v2.0_cls_infer",
+            rec_model_dir="paddleocr/model/ch_PP-OCRv3_rec_infer",
+            det_model_dir="paddleocr/model/en_PP-OCRv3_det_infer")
+        return ocr
+    def paddle_ocr_prediction(self,img_path, ocr):
+        result = ocr.ocr(img_path, cls=False, det=True, rec=True)[0]
+        txts = [line[1][0] for line in result]
+        return txts
+
+    def check_character(self,character):
+        if len(character) < 17:
+            return False
+        else:
+            return character
+
+    def fixed_character(self,character):
+        if character[len(fixed) + len(internal)] not in year_list:
+            return False
+
+        if fixed != character[0:len(fixed)]:
+            return False
+        if internal != character[len(fixed):len(fixed) + len(internal)]:
+            return False
+        if plant_name != character[len(fixed) + len(internal) + 1]:
+            return False
+        if character[len(fixed) + len(internal) + 2] not in month_list:
+            return False
+        return character
+    def craft_character_find(self):
+        # read image
+        image = read_image(image)
+
+        # load models
+        refine_net = load_refinenet_model(cuda=False)
+        craft_net = load_craftnet_model(cuda=False)
+
+        # perform prediction
+        prediction_result = get_prediction(
+            image=image,
+            craft_net=craft_net,
+            refine_net=refine_net,
+            text_threshold=0.7,
+            link_threshold=9999999999999999999,
+            low_text=0.4,
+            cuda=False,
+            long_size=1280
+        )
+
+        # export detected text regions
+        exported_file_paths = export_detected_regions(
+            image=image,
+            regions=prediction_result["boxes"],
+            output_dir=output_dir,
+            rectify=True
+        )
+
+        # export heatmap, detection points, box visualization
+        export_extra_results(
+            image=image,
+            regions=prediction_result["boxes"],
+            heatmaps=prediction_result["heatmaps"],
+            output_dir=output_dir
+        )
+
+        # unload models from gpu
+        empty_cuda_cache()
+        print("find")
+    def classify_last_eight_chacter(self):
+        print("8")
+    def verify_mont_year_plant(self):
+        print("month")
+    def compare_to_get_final_output(self):
+        print("output")
+    def final_output(self):
+        prediction="success"
+        print(prediction)
+
+    def _pre_process(self, x):
+        """
+        Do preprocessing here, if any
+        :param x: payload
+        :return: payload
+        """
+        return x
+
+    def _post_process(self, x):
+        """
+        Apply post processing here, if any
+        :param x: payload
+        :return: payload
+        """
+        self.rtp.publish(x)  # video stream
+        return x
+
+    def send_payload(self, frame, bag_type='', label='CementBagDetected', bg_color="#474520", font_color="#FFFF00",
+                     alert_sound=None,
+                     message="Cement Bag Detected!", mrp_frmae='', mrp_roi = '', mrp = ''):
+        """
+        Insert event to Mongo
+        :param message:
+        :param frame:
+        :param label:
+        :param bg_color:
+        :param font_color:
+        :param alert_sound:
+        :return: None
+        """
+
+        payload = {"deviceId": self.device_id, "message": message,
+                   "frame": 'data:image/jpeg;base64,' + base64.b64encode(
+                       cv2.imencode('.jpg', frame)[1].tostring()).decode("utf-8"), "activity": label,
+                   "bg_color": bg_color, "font_color": font_color, "alert_sound": alert_sound, "bag_type": bag_type,
+                   "mrp_frmae": mrp_frmae, "mrp_roi" : mrp_roi, "mrp" : mrp}
+
+        self.mongo_logger.insert_attendance_event_to_mongo(payload)
+
+    def kalman_tracker(
+            self,
+            bboxs,
+            img,
+    ):
+
+        z_box = bboxs
+        x_box = []
+
+        if len(self.tracker_list) > 0:
+            for trk in self.tracker_list:
+                x_box.append(trk.box)
+
+        matched, unmatched_dets, unmatched_trks = self.assign_detections_to_trackers(x_box, z_box, iou_thrd=0.03)
+
+        # Deal with matched detections
+        if matched.size > 0:
+            for trk_idx, det_idx in matched:
+                z = z_box[det_idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.kalman_filter(z)
+                xx = tmp_trk.x_state.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                x_box[trk_idx] = xx
+                tmp_trk.box = xx
+                tmp_trk.hits += 1
+
+        # Deal with unmatched detections
+        if len(unmatched_dets) > 0:
+            for idx in unmatched_dets:
+                z = z_box[idx]
+                z = np.expand_dims(z, axis=0).T
+                tmp_trk = Tracker()  # Create a new tracker
+                x = np.array([[z[0], 0, z[1], 0, z[2], 0, z[3], 0]]).T
+                tmp_trk.x_state = x
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                tmp_trk.id = self.track_id_list.popleft()  # assign an ID for the tracker
+
+                self.tracker_list.append(tmp_trk)
+                x_box.append(xx)
+
+        # Deal with unmatched tracks
+        if len(unmatched_trks) > 0:
+            for trk_idx in unmatched_trks:
+                tmp_trk = self.tracker_list[trk_idx]
+                tmp_trk.no_losses += 1
+                tmp_trk.predict_only()
+                xx = tmp_trk.x_state
+                xx = xx.T[0].tolist()
+                xx = [xx[0], xx[2], xx[4], xx[6]]
+                tmp_trk.box = xx
+                x_box[trk_idx] = xx
+
+        # The list of tracks to be annotated
+        good_tracker_list = []
+        objects = []
+        boxs = []
+        for trk in self.tracker_list:
+            if (trk.hits >= self.min_hits) and (trk.no_losses <= self.max_age):
+                good_tracker_list.append(trk)
+                x_cv2 = trk.box
+                left, top, right, bottom = x_cv2[1], x_cv2[0], x_cv2[3], x_cv2[2]
+                centroid = [int(left + ((right - left) / 2)), bottom]
+                objects.append([int(trk.id), centroid])
+                boxs.append(x_cv2)
+
+        deleted_tracks = filter(lambda _x: _x.no_losses > self.max_age, self.tracker_list)
+
+        for trk in deleted_tracks:
+            self.track_id_list.append(trk.id)
+
+        self.tracker_list = [x for x in self.tracker_list if x.no_losses <= self.max_age]
+        # print("object is ", str(objects))
+
+        return img, objects, boxs
+
+    @staticmethod
+    def assign_detections_to_trackers(
+            trackers,
+            detections,
+            iou_thrd=0.3,
+    ):
+        """
+        From current list of trackers and new detections, output matched detections,
+        un matched trackers, unmatched detections.
+        """
+        iou_mat = np.zeros((len(trackers), len(detections)), dtype=np.float32)
+        for t, trk in enumerate(trackers):
+            for d, det in enumerate(detections):
+                iou_mat[t, d] = box_iou2(trk, det)
+
+        matched_idx = linear_assignment(-iou_mat)
+
+        unmatched_trackers, unmatched_detections = [], []
+        for t, trk in enumerate(trackers):
+            if t not in matched_idx[:, 0]:
+                unmatched_trackers.append(t)
+
+        for d, det in enumerate(detections):
+            if d not in matched_idx[:, 1]:
+                unmatched_detections.append(d)
+
+        matches = []
+
+        for m in matched_idx:
+            if iou_mat[m[0], m[1]] < iou_thrd:
+                unmatched_trackers.append(m[0])
+                unmatched_detections.append(m[1])
+            else:
+                matches.append(m.reshape(1, 2))
+
+        if len(matches) == 0:
+            matches = np.empty((0, 2), dtype=int)
+        else:
+            matches = np.concatenate(matches, axis=0)
+
+        return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
+
+    def get_line_coordinates(self):
+        """
+        Get the line coordinates from the deployment JSON
+        """
+        if not self.janus_metadata.get('metadata'):
+            self.janus_metadata['metadata'] = get_extra_fields(self.device_id)
+
+        _coordinates = [self.janus_metadata['metadata'].get(coordinate_key) for coordinate_key in
+                        JanusDeploymentConstants.LINE_COORDINATES]
+        _alignment = self.janus_metadata['metadata'].get(JanusDeploymentConstants.ALIGNMENT_KEY) \
+            # _coordinates = [550, 200, 555, 1100]
+        #
+        # _alignment = "vertical"
+        return _alignment, _coordinates
+
+    def line_point_position(self, point):
+        """
+        Get the position of point w.r.t. the line
+        :param point: point to be compared
+        :return: boolean
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+        assert len(point) == 2, "Point variable is invalid"
+
+        _slope = (line_coordinates[3] - line_coordinates[1]) / (line_coordinates[2] - line_coordinates[0])
+        _point_equation_value = point[1] - line_coordinates[1] - _slope * (point[0] - line_coordinates[0])
+        if _point_equation_value > 0:
+            return True
+        else:
+            return False
+
+    def insert_alarm_event(self, message="MRP Missing", asset_hierarchy=""):
+        data = {
+            "device_instance_id": asset_hierarchy,
+            "device_instance_ids": asset_hierarchy,
+            "alarm_id": "alarm_configuration_212",
+            "triggered_devices": [
+                asset_hierarchy
+            ],
+            "tag_value": 5.0,
+            "start_time": None,
+            "end_time": "",
+            "current_level": 0,
+            "id": "alarm_event_1567101",
+            "trigger_time": [
+                {
+                    "start_time": None,
+                    "counter": 0
+                }
+            ],
+            "trigger_levels": [
+                {
+                    "timestamp": None,
+                    "notificaton_profile": [
+                        {
+                            "usersOrUserGroup": [
+                                {
+                                    "value": "access_group_100",
+                                    "type": "access_group",
+                                    "label": "ACC Admin"
+                                }
+                            ],
+                            "notificationProfile": [
+                                "alarm_notify_type_4"
+                            ],
+                            "emailIds": [],
+                            "phoneNumbers": [],
+                            "notificationTone": "",
+                            "isNotificationToneShow": True,
+                            "triggers": [
+                                {
+                                    "device_instance_id": None,
+                                    "tags": None,
+                                    "customValueType": None,
+                                    "customValue": None,
+                                    "counter": 1
+                                }
+                            ],
+                            "counter": 1,
+                            "enable_custom": True
+                        }
+                    ]
+                }
+            ],
+            "priority": "alarm_priority_type_109",
+            "tag_id": "",
+            "template": "MRP Missing",
+            "acknowledge": True,
+            "alarmName": message,
+            "alarmType": "Alarm",
+            "created_by": "user_100",
+            "project_id": "project_101",
+            "product_encrypted": False,
+            "start_time_in_epoch": None,
+            "show_data_viz": True,
+            "alarm_condition": message,
+            "tag_id_list": [
+                asset_hierarchy
+            ],
+            "tag_value_json": {
+                asset_hierarchy: 5.0
+            },
+            "alarm_tag_list": [
+                asset_hierarchy
+            ],
+            "acknowledged_at": "2022-01-06 20:51:22",
+            "acknowledged_by": None
+        }
+        epoch = int(time.time()) * 1000
+        time_string = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")
+        data['start_time_in_epoch'] = epoch
+        data['trigger_time'][0]['start_time'] = epoch
+        data['start_time'] = time_string
+        data['trigger_levels'][0]['timestamp'] = time_string
+        data['acknowledged_at'] = time_string
+        data['id'] = f"alarm_event_{str(uuid4()).split('-')[0]}"
+        self.mongo_alarm_coll.insert_one(data)
+
+    def validate_point_position(self, point):
+        """
+        Validate the position of the point w.r.t. the line
+        :param point: centroid
+        :return: bool
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert _alignment in [JanusDeploymentConstants.VERTICAL, JanusDeploymentConstants.HORIZONTAL], \
+            "Invalid alignment variable"
+        if _alignment == JanusDeploymentConstants.VERTICAL:
+            # _alignment, line_coordinates = self.get_line_coordinates()
+            # assert _alignment in ["horizontal", "vertical"], \
+            #     "Invalid alignment variable"
+            # print(point)
+            # if _alignment == "vertical":
+            line_y2 = line_coordinates[3]
+            line_y1 = line_coordinates[1]
+            if line_y1 < point[1] < line_y2 or line_y2 < point[1] < line_y1:
+                return True
+            else:
+                return False
+        else:
+            line_x2 = line_coordinates[2]
+            line_x1 = line_coordinates[0]
+            if line_x1 < point[0] < line_x2 or line_x2 < point[0] < line_x1:
+
+                return True
+            else:
+                return False
+
+    # def verifying_cement_bag_type(self, previous_class, current_class):
+    #     if(previous_class == current_class):
+    #         print("bag changed")
+
+    def update_bag_count(self, frame, detection_objects, class_name, detections):
+        """
+        Maintains the bag counts
+        :param frame: image
+        :param detection_objects: detection object having object id and centroids
+        """
+        # for class_name, (objectID, centroid) in zip(classes, detection_objects):
+        for (object_id, det, class_detected) in zip(
+                detection_objects, detections, class_name
+        ):
+            centroid = object_id[1]
+            object_id = object_id[0]
+            logger.debug(detections)
+            # print(object_id)
+            frame = draw_circles_on_frame(
+                frame, centroid, radius=10, color=(0, 0, 255), thickness=-1
+            )
+            if self.validate_point_position(centroid):
+                logger.debug("centroid detected")
+
+                if not isinstance(self.initial_object_position, bool):
+                    logger.debug("Initializing the initial object position")
+                    # self.initial_object_position = self.line_point_position(point=centroid)
+                    self.initial_object_position = True
+                    logger.debug(self.initial_object_position)
+
+                _point_position = self.line_point_position(point=centroid)
+                # print("object ID is : ", str(objectID))
+                logger.debug(self.uncounted_objects)
+
+                # Check point in the same side as the initial object
+                if _point_position == self.initial_object_position:
+                    logger.debug("same side only")
+                    # print(class_name)
+                    # Check the object is not already counted
+                    if object_id not in self.uncounted_objects:
+                        self.uncounted_objects[object_id] = centroid
+
+                elif object_id in self.uncounted_objects:
+                    # print("************")
+                    # print(class_detected)
+                    self.uncounted_objects.pop(object_id, None)
+
+                    if class_detected == "acc_gold":
+                        gold_flag = self.yellow_thresholding(
+                            detections, frame, class_detected
+                        )
+                        if gold_flag:
+                            self.count_gold += 1
+                        else:
+                            self.count_suraksha += 1
+                            # self.verifying_cement_bag_type(self.prev_class_name, "acc_gold")
+                            # self.prev_class_name = "acc_gold"
+                            class_detected = "acc_suraksha_power_plus"
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi,
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            if gold_flag:
+                                self.send_payload(
+                                    resize_to_64_64(frame=frame),
+                                    bag_type="acc_gold",
+                                    message="ACC GOLD, MRP:YES",
+                                    mrp_frmae=mrp_frame,
+                                    mrp_roi=mrp_roi,
+                                    mrp="PASS",
+                                )
+                                logger.info(
+                                    f"Count: {self.count_gold}, Print Found: True"
+                                )
+                            else:
+                                self.send_payload(
+                                    resize_to_64_64(frame=frame),
+                                    bag_type="acc_suraksha_power_plus",
+                                    message="ACC SURAKSHA PP, MRP:YES",
+                                    mrp_frmae=mrp_frame,
+                                    mrp_roi=mrp_roi,
+                                    mrp="PASS",
+                                )
+                                logger.info(
+                                    f"Count: {self.count_suraksha}, Print Found: True"
+                                )
+
+                        else:
+                            if gold_flag:
+                                self.send_payload(
+                                    resize_to_64_64(frame=frame),
+                                    bag_type="acc_gold",
+                                    message="ACC GOLD, MRP:NO",
+                                    mrp_frmae=mrp_frame,
+                                    mrp_roi=mrp_roi,
+                                )
+                                logger.info(
+                                    f"Count: {self.count_gold}, Print Found: False"
+                                )
+
+                            else:
+                                self.send_payload(
+                                    resize_to_64_64(frame=frame),
+                                    bag_type="acc_suraksha_power_plus",
+                                    message="ACC SURAKSHA PP, MRP:NO",
+                                    mrp_frmae=mrp_frame,
+                                    mrp_roi=mrp_roi,
+                                )
+                                logger.info(
+                                    f"Count: {self.count_suraksha}, Print Found: False"
+                                )
+
+                    elif class_detected == "acc_suraksha_power_plus":
+                        self.count_suraksha += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "acc_suraksha")
+                        # self.prev_class_name = "acc_suraksha"
+                        logger.debug(self.count_suraksha)
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_suraksha_power_plus",
+                                message="ACC SURAKSHA PP, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(
+                                f"Count: {self.count_suraksha}, Print Found: True"
+                            )
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_suraksha_power_plus",
+                                message="ACC SURAKSHA PP, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(
+                                f"Count: {self.count_suraksha}, Print Found: False"
+                            )
+
+                    elif class_detected == "ambuja_buildcem":
+                        self.count_whitecem += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "ambuja_buildcem")
+                        # self.prev_class_name = "ambuja_buildcem"
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="ambuja_buildcem",
+                                message="AMBUJA BUILDCEM, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(
+                                f"Count: {self.count_whitecem}, Print Found: True"
+                            )
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="ambuja_buildcem",
+                                message="AMBUJA BUILDCEM, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(
+                                f"Count: {self.count_whitecem}, Print Found: False"
+                            )
+
+                    elif class_detected == "acc_nfr":
+                        self.count_nfr += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "acc_nfr")
+                        # self.prev_class_name = "acc_nfr"
+                        logger.debug(self.count_nfr)
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi,
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_nfr",
+                                message="ACC NFR, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(f"Count: {self.count_nfr}, Print Found: True")
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_nfr",
+                                message="ACC NFR, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(f"Count: {self.count_nfr}, Print Found: False")
+
+                    elif class_detected == "acc_suraksha_power":
+                        self.count_suraksha_power += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "acc_suraksha_power")
+                        # self.prev_class_name = "acc_suraksha_power"
+                        logger.debug(self.count_suraksha_power)
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi,
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_suraksha_power",
+                                message="ACC SURAKSHA POWER, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(
+                                f"Count: {self.count_suraksha_power}, Print Found: True"
+                            )
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_suraksha_power",
+                                message="ACC SURAKSHA POWER, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(
+                                f"Count: {self.count_suraksha_power}, Print Found: False"
+                            )
+
+                    elif class_detected == "acc_concrete_plus":
+                        self.count_concrete_plus += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "acc_nfr")
+                        # self.prev_class_name = "acc_nfr"
+                        logger.debug(self.count_concrete_plus)
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi,
+                        ) = self.distances(detections, frame, class_detected)
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_concrete_plus",
+                                message="ACC CONCRETE PLUS, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(
+                                f"Count: {self.count_concrete_plus}, Print Found: True"
+                            )
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="acc_concrete_plus",
+                                message="ACC CONCRETE PLUS, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(
+                                f"Count: {self.count_concrete_plus}, Print Found: False"
+                            )
+
+                    elif class_detected == "ambuja_plus":
+                        self.count_ambuja_plus += 1
+                        # self.verifying_cement_bag_type(self.prev_class_name, "acc_nfr")
+                        # self.prev_class_name = "acc_nfr"
+                        logger.debug(self.count_ambuja_plus)
+                        (
+                            mrp_result,
+                            mrp_frame,
+                            mrp_roi,
+                        ) = self.distances(detections, frame, class_detected)
+                        self.text = "COUNT : {ambuja_count}/10".format(
+                            ambuja_count=self.count_ambuja_plus
+                        )
+
+                        if mrp_result:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="ambuja_plus",
+                                message="Ambuja PLUS, MRP:YES",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                                mrp="PASS",
+                            )
+                            logger.info(
+                                f"Count: {self.count_ambuja_plus}, Print Found: True"
+                            )
+                        else:
+                            self.send_payload(
+                                resize_to_64_64(frame=frame),
+                                bag_type="ambuja_plus",
+                                message="Ambuja PLUS, MRP:NO",
+                                mrp_frmae=mrp_frame,
+                                mrp_roi=mrp_roi,
+                            )
+                            logger.info(
+                                f"Count: {self.count_ambuja_plus}, Print Found: False"
+                            )
+
+                    frame = draw_circles_on_frame(
+                        frame, centroid, radius=10, color=(0, 255, 0), thickness=-1
+                    )
+                    # cv2.waitKey(0)
+                    # if centroid['has_print']:
+                    #     self.send_payload(resize_to_64_64(frame=frame), message='Print Detected!')
+                    #     logger.info(f"Count: {self.count}, Print Found: True")
+                    # else:
+                    #     self.send_payload(resize_to_64_64(frame=frame), message='Print Missing!')
+                    #     logger.info(f"Count: {self.count}, Print Found: False")
+                else:
+                    frame = draw_circles_on_frame(
+                        frame, centroid, radius=10, color=(0, 255, 0), thickness=-1
+                    )
+
+        # count_text_gold = "ACC_GOLD: " + str(self.count_gold)
+        # count_text_suraksha = "ACC_SURAKSHA_PLUS: " + str(self.count_suraksha)
+        # count_text_whitecem = "ACC_WHITE_CEM: " + str(self.count_whitecem)
+        # count_text_suraksha_power = "ACC_SURAKSHA_POWER: " + str(self.count_suraksha_power)
+        # count_text_nfr = "ACC_NFR: " + str(self.count_nfr)
+        # cv2.putText(frame, count_text_gold, (1300, 200), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_suraksha, (1300, 400), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_whitecem, (1300, 600), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_suraksha_power, (1300, 800), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, count_text_nfr, (1300, 1000), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        # cv2.putText(frame, self.prev_class_name, (1000, 800), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 3,
+        #             cv2.LINE_AA)
+        return frame
+
+    def yellow_thresholding(self, detections, frame, class_detected):
+        gold_flag = False
+        mrp_cord = []
+        cem_bag_cord = []
+        add_mrp = ""
+        for det in detections:
+            if det["class"] == "mrp":
+                mrp_cord.append(det["points"])
+            else:
+                cem_bag_cord.append(det["points"])
+
+        for c_cord in cem_bag_cord:
+
+            bag_width = c_cord[2] - c_cord[0]
+            if bag_width > 500:
+                roi = frame[c_cord[1] + 40: c_cord[3], c_cord[0]: c_cord[2] - 80]
+        original = roi.copy()
+        # cv2.imshow("roi", roi)
+        # cv2.waitKey(0)
+
+        image = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
+
+        lower = np.array([10, 70, 0], dtype="uint8")
+        upper = np.array([45, 255, 255], dtype="uint8")
+        mask = cv2.inRange(image, lower, upper)
+
+        cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        cnts = cnts[0] if len(cnts) == 2 else cnts[1]
+        # print("contours")
+        # print(len(cnts))
+
+        for c in cnts:
+            x, y, w, h = cv2.boundingRect(c)
+            # cv2.imshow("bag with yellow region:  {w}".format(w=w), original)
+            # print(x, y, w, h)
+            if w > 100:
+                gold_flag = True
+                cv2.rectangle(original, (x, y), (x + w, y + h), (36, 255, 12), 2)
+                #
+                break
+        # if gold_flag:
+        #     print("Final Bag: ACC Gold")
+        # else:
+        #     print("Final Bag: ACC SURAKSHA PP")
+
+        return gold_flag
+
+    def draw_line_over_image(self, frame, color=(255, 255, 255)):
+        """
+        Draws line over the counting line
+        :param frame: frame for
+        :param color:
+        :return:
+        """
+        _alignment, line_coordinates = self.get_line_coordinates()
+        assert len(line_coordinates) == 4, "Line coordinates variable is invalid"
+
+        # return cv2.line(frame, (line_coordinates[0], line_coordinates[1]), (line_coordinates[2], line_coordinates[3]),
+        #                 color, 3)
+
+        self.drawline(
+            frame,
+            (line_coordinates[0], line_coordinates[1]),
+            (line_coordinates[2], line_coordinates[3]),
+            color,
+            thickness=3,
+        )
+        return frame
+
+    @staticmethod
+    def drawline(img, pt1, pt2, color, thickness=1, style="dotted", gap=20):
+        dist = ((pt1[0] - pt2[0]) ** 2 + (pt1[1] - pt2[1]) ** 2) ** 0.5
+        pts = []
+        for i in np.arange(0, dist, gap):
+            r = i / dist
+            x = int((pt1[0] * (1 - r) + pt2[0] * r) + 0.5)
+            y = int((pt1[1] * (1 - r) + pt2[1] * r) + 0.5)
+            p = (x, y)
+            pts.append(p)
+
+        if style == "dotted":
+            for p in pts:
+                cv2.circle(img, p, thickness, color, -1)
+        else:
+            s = pts[0]
+            e = pts[0]
+            i = 0
+            for p in pts:
+                s = e
+                e = p
+                if i % 2 == 1:
+                    cv2.line(img, s, e, color, thickness)
+                i += 1
+
+    def crop_polygon(self, cement_bag_img):
+        pts = np.array([[100, 180], [530, 110], [555, 190], [100, 260]])
+
+        ## (1) Crop the bounding rect
+        rect = cv2.boundingRect(pts)
+        x, y, w, h = rect
+        croped = cement_bag_img[y: y + h, x: x + w].copy()
+
+        ## (2) make mask
+        pts = pts - pts.min(axis=0)
+
+        mask = np.zeros(croped.shape[:2], np.uint8)
+        cv2.drawContours(mask, [pts], -1, (255, 255, 255), -1, cv2.LINE_AA)
+
+        ## (3) do bit-op
+        dst = cv2.bitwise_and(croped, croped, mask=mask)
+
+        ## (4) add the white background
+        bg = np.ones_like(croped, np.uint8) * 255
+        cv2.bitwise_not(bg, bg, mask=mask)
+        mrp_tag = bg + dst
+        # import random
+        #
+        # cv2.imwrite(
+        #     "E:\\acc_new\\mrp_region_only\\{random_number}.jpg".format(
+        #         random_number=random.randint(1, 100000)
+        #     ),
+        #     mrp_tag,
+        # )
+        return mrp_tag
+
+    def mrp_digit_count(self, img, detected_class):
+        digit_num = {"ambuja_plus": 17, "acc_gold": 13, "acc_suraksha_power_plus": 17}
+        height, width = img.shape[:2]
+        # print(height, width)
+        # img[45: 95, 290:379] = [255, 255, 255]
+        # img[25: 95, 290:500] = [255, 255, 255]
+        bag_type = detected_class
+
+        blank_image = np.zeros((300, 800, 3), np.uint8)
+
+        blank_image[:, :] = (255, 255, 255)
+
+        l_img = blank_image.copy()  # (600, 900, 3)
+
+        x_offset = y_offset = 20
+
+        l_img[y_offset: y_offset + height, x_offset: x_offset + width] = img.copy()
+
+        # cv2.imshow("l_img", l_img)
+
+        img = l_img
+
+        if bag_type == "ambuja_plus":
+            hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+
+            h, s, v = cv2.split(hsv)
+
+            th, threshed = cv2.threshold(v, 220, 255, cv2.THRESH_BINARY_INV)
+
+            image = cv2.bitwise_and(img, img, mask=threshed)
+            # cv2.imshow("thresholded_image", image)
+
+            # pre-process the image by resizing it, converting it to
+
+            # graycale, blurring it, and computing an edge map
+
+            image = imutils.resize(image, height=150)
+
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+            blurred = cv2.GaussianBlur(gray, (5, 5), 0)
+
+            edged = cv2.Canny(blurred, 50, 200, 255)
+            # cv2.imshow("edged", edged)
+            thresh = cv2.threshold(
+                blurred, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU
+            )[1]
+
+            # print("After Threshold")
+
+            # cv2.imshow("thresh", thresh)
+
+            kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_OPEN, kernel, np.ones((5, 5), np.uint8), iterations=2
+            )
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_CLOSE, kernel, None, None, 1, cv2.BORDER_REFLECT101
+            )
+
+            # cv2.imshow("thresh2", thresh)
+            cnts = cv2.findContours(
+                thresh.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
+            )
+
+            cnts = imutils.grab_contours(cnts)
+
+            cv2.drawContours(
+                thresh,
+                cnts,
+                -1,
+                (0, 0, 255),
+                1,
+            )
+
+            x = self.find_chars(cnts, thresh)
+
+        if bag_type == "acc_suraksha_power_plus":
+            hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+
+            h, s, v = cv2.split(hsv)
+
+            th, threshed = cv2.threshold(v, 220, 255, cv2.THRESH_BINARY_INV)
+
+            image = cv2.bitwise_and(img, img, mask=threshed)
+
+            # pre-process the image by resizing it, converting it to
+
+            # graycale, blurring it, and computing an edge map
+
+            image = imutils.resize(image, height=150)
+
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+            blurred = cv2.GaussianBlur(gray, (5, 5), 0)
+
+            edged = cv2.Canny(blurred, 50, 200, 255)
+
+            thresh = cv2.threshold(
+                blurred, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU
+            )[1]
+
+            # print("After Threshold")
+
+            # cv2.imshow("thresh4", thresh)
+
+            kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7, 7))
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_OPEN, kernel, np.ones((5, 5), np.uint8), iterations=2
+            )
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_CLOSE, kernel, None, None, 1, cv2.BORDER_REFLECT101
+            )
+
+            # print("After Morphology")
+
+            # cv2.imshow("thresh5", thresh)
+
+            # find contours in the thresholded image, then initialize the
+
+            # digit contours lists
+
+            cnts = cv2.findContours(thresh.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
+
+            cnts = imutils.grab_contours(cnts)
+
+            cv2.drawContours(
+                thresh,
+                cnts,
+                -1,
+                (0, 255, 0),
+                1,
+            )
+
+            # cv2.imshow("thresh6", thresh)
+
+            x = self.find_chars(cnts, thresh)
+
+        if bag_type == "acc_gold":
+            hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+
+            h, s, v = cv2.split(hsv)
+
+            # cv2.imshow("img", img)
+
+            th, threshed = cv2.threshold(v, 220, 255, cv2.THRESH_BINARY_INV)
+
+            image = cv2.bitwise_and(img, img, mask=threshed)
+            # cv2.imshow("bitwise and", image)
+
+            # pre-process the image by resizing it, converting it to
+
+            # graycale, blurring it, and computing an edge map
+
+            image = imutils.resize(image, height=150)
+
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+            blurred = cv2.GaussianBlur(gray, (5, 5), 0)
+
+            edged = cv2.Canny(blurred, 50, 200, 255)
+
+            thresh = cv2.threshold(
+                blurred, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU
+            )[1]
+
+            # cv2.imshow("thresh7", thresh)
+
+            kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_OPEN, kernel, np.ones((5, 5), np.uint8), iterations=2
+            )
+
+            thresh = cv2.morphologyEx(
+                thresh, cv2.MORPH_CLOSE, kernel, None, None, 1, cv2.BORDER_REFLECT101
+            )
+
+            # cv2.imshow("thresh9", thresh)
+
+            # find contours in the thresholded image, then initialize the
+
+            # digit contours lists
+
+            cnts = cv2.findContours(thresh.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
+
+            cnts = imutils.grab_contours(cnts)
+
+            cv2.drawContours(
+                thresh,
+                cnts,
+                -1,
+                (0, 255, 0),
+                1,
+            )
+
+            # cv2.imshow("thresh10", thresh)
+
+            x = self.find_chars(cnts, thresh)
+
+        # cv2.imshow("thresh11", thresh)
+
+        if x >= (digit_num[detected_class] - 2):
+            return x, True
+        else:
+            return x, False
+
+    def distances(self, detections, frame, class_detected):
+
+        mrp_cord = []
+        cem_bag_cord = []
+        add_mrp = ""
+        mrp_roi = ""
+        for det in detections:
+            if det["class"] == "mrp":
+                mrp_cord.append(det["points"])
+            else:
+                cem_bag_cord.append(det["points"])
+
+        # if mrp_cord == []:
+        #     return False, add_mrp, mrp_roi
+
+        for c_cord in cem_bag_cord:
+
+            bag_width = c_cord[2] - c_cord[0]
+            if bag_width > 500:
+                roi = frame[c_cord[1]: c_cord[3], c_cord[0]: c_cord[2]]
+                # cv2.imwrite("E:\\acc_new\\masked_bag_ambuja_\\{count}.jpg".format(count = self.count), roi)
+                # self.count+= 1
+                h, w, _ = roi.shape
+                # cv2.imshow("cement_bag", roi)
+                roi_half_h = roi[int((h / 2) - 0): h, 0:w]
+
+                roi_half_v = roi_half_h[50: int((h / 2)), 0: w - 150]
+                # cv2.imshow("roi", roi)
+                mrp_roi = "data:image/jpeg;base64," + base64.b64encode(
+                    cv2.imencode(".jpg", roi)[1].tostring()
+                ).decode("utf-8")
+
+                extra_values = get_extra_fields(self.device_id)
+                mrp_detect = extra_values.get(JanusDeploymentConstants.MRP_DETECT_KEY)
+                if mrp_detect is not None and mrp_detect.lower() == "yes":
+                    mrp_add = self.mrp_image(roi_half_v, class_detected)
+                    # cv2.imshow("mrp_add", mrp_add)
+                    if mrp_add is not None:
+                    #     mrp_region = self.crop_polygon(roi)
+                    #     # cv2.imshow("mrp_region_", mrp_region)
+                    #     mrp_digits, mrp_status = self.mrp_digit_count(
+                    #         mrp_region, class_detected
+                    #     )
+                    #     # cv2.waitKey(0)
+                    #     if mrp_status:
+                    #         mrp_check = "PASS"
+                    #     else:
+                    #         mrp_check = "FAIL"
+
+                        # cv2.imshow("mrp yes", cv2.resize(mrp_add, (400, 300)))
+                        self.mrp_counter = 0
+                        add_mrp = "data:image/jpeg;base64," + base64.b64encode(
+                            cv2.imencode(".jpg", mrp_add)[1].tostring()
+                        ).decode("utf-8")
+                        return True, add_mrp, mrp_roi
+
+                    else:
+                        # cv2.imshow("mrp no", mrp_add)
+                        self.mrp_counter += 1
+                        if self.mrp_counter >= 5:
+                            self.mrp_counter = 0
+                            logger.debug("activate relay")
+                            self.insert_alarm_event(
+                                asset_hierarchy=self.camera_details.get(
+                                    "asset_hierarchy", ""
+                                ),
+                                message=self.camera_details.get("asset_name", "")
+                                        + " - "
+                                        + class_detected
+                                        + " : MRP missed",
+                            )
+                            RelayHandler().update_relay_status(
+                                self.camera_details.get("belt_relay_ep", ""),
+                                dict(triggerStatus="stop"),
+                            )
+                            logger.debug(
+                                "Stopped the relay because of 5 consecutive MRP misses"
+                            )
+
+                        return False, add_mrp, mrp_roi
+
+
+
+
+    def inference(
+            self,
+            frame,
+            classes,
+
+    ):
+        # TRT Additions start
+
+        # dets = self.yp.predict(frame)
+        result_boxes, result_scores, result_classid = self.yolo_v5_wrapper.infer(frame)
+        dets = [{"points": list(points), "conf": conf, "class": self.classes.get(class_id)} for points, conf, class_id
+                in
+                zip(result_boxes, result_scores, result_classid)]
+        # TRT Additions stop
+
+        class_name = list()
+        bboxs = []
+
+        if dets:
+            for i in dets:
+                if (i["class"] in classes):
+                    class_name.append(i["class"])
+                    # cv2.rectangle(frame, (i["points"][0], i["points"][1]), (i["points"][2], i["points"][3]), (255, 255, 0), 2)
+                    bboxs.append([i["points"][1], i["points"][0], i["points"][3], i["points"][2]])
+
+        #        frame = cv2.rectangle(frame, (bboxs[0][0], bboxs[0][1]), (bboxs[0][2], bboxs[0][3]),(255, 255, 0) , 2)
+        return bboxs, frame, dets, class_name
+
+    def _predict(self, obj):
+        class_list = ["acc_gold", "acc_suraksha_power_plus", "ambuja_buildcem", "acc_nfr", "acc_suraksha_power",
+                      "acc_concrete_plus", "ambuja_plus"]
+        mrp = ["mrp"]
+        try:
+            frame = obj['frame']
+
+            dets, frame, _dets, class_name = self.inference(frame, class_list)
+
+            frame = self.draw_line_over_image(frame)
+
+            frame, objects, boxs = self.kalman_tracker(dets, frame)
+
+            frame = self.update_bag_count(frame=frame, detection_objects=objects, class_name=class_name,
+                                          detections=_dets)
+
+            logger.debug("self.uncounted_objects --> {}".format(self.uncounted_objects))
+
+            obj['frame'] = cv2.resize(frame, (self.config.get('FRAME_WIDTH'), self.config.
+                                              get('FRAME_HEIGHT')))
+        except Exception as e:
+            logger.exception(f"Error: {e}", exc_info=True)
+            obj['frame'] = cv2.resize(obj['frame'], (self.config.get('FRAME_WIDTH'), self.config.get('FRAME_HEIGHT')))
+
+        return obj
+
+
+    def detect_mrp(self, img, class_detected):
+
+        # print("Finding Pixels")
+        black_pixel = 0
+        white_pixel = 100
+        # img_bgr = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+        pixels = img.reshape(-1, 3)
+        for pixel in pixels:
+            if pixel[0] == pixel[1] == pixel[2] == 0:
+                black_pixel += 1
+            else:
+                white_pixel += 1
+
+        black_to_white = (white_pixel / black_pixel) * 100
+
+        black_white_ratio = self.black_white_ratio_dict[
+            "{class_name}".format(class_name=class_detected)
+        ]
+        # print("black_white_ratio")
+        # print(black_white_ratio)
+        # cv2.imshow("black white ratio {black_white_ratio1}.jpg".format(black_white_ratio1=str(black_to_white)),
+        #            img)
+        # if(black_to_white == 14.99204665959703):
+        #     cv2.imwrite("black white ratio {black_white_ratio1}".format(black_white_ratio1=str(black_to_white)), img)
+        if int(black_to_white) < int(black_white_ratio):
+            flag = False
+        else:
+            # print("MRP present, finding MRP region..")
+            flag = True
+        return flag
+
+    def mrp_image(self, img, class_detected):
+        ROI = None
+        try:
+            # cv2.imshow("roi image", img)
+            img_cp = img.copy()
+            rgb_planes = cv2.split(img_cp)
+            kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]])
+
+            result_planes = []
+            for plane in rgb_planes:
+                dilated_img = cv2.dilate(plane, np.ones((7, 7), np.uint8))
+                bg_img = cv2.medianBlur(dilated_img, 21)
+                diff_img = 255 - cv2.absdiff(plane, bg_img)
+                result_planes.append(diff_img)
+
+            result = cv2.merge(result_planes)
+            # print("Original Image but cropped,and shadow removed")
+            # cv2.imshow("shadow_removed", result)_predict
+            shadow_removed = result.copy()
+
+            result = cv2.filter2D(src=result, ddepth=-1, kernel=kernel)
+            # cv2_imshow(result)
+
+            img_cp = result
+            # Convert BGR to HSV
+            hsv = cv2.cvtColor(img_cp, cv2.COLOR_BGR2HSV)
+
+            # define range of black color in HSV
+            lower_val = np.array([0, 0, 160])
+            upper_val = np.array([180, 230, 200])
+
+            # Threshold the HSV image to get only black colors
+            mask = cv2.inRange(hsv, lower_val, upper_val)
+
+            # Bitwise-AND mask and original image
+            res = cv2.bitwise_and(img_cp, img_cp, mask=mask)
+
+            mrp_flag = self.detect_mrp(res, class_detected)
+            if not mrp_flag:
+                return ROI
+            else:
+                # cv2.imshow("res", res)
+                return res
+
+        except Exception as e:
+            logger.exception(f"Error: {e}", exc_info=True)
+            return ROI
\ No newline at end of file

scripts/common/config.py

+import os
+import sys
+import json
+
+from pymongo import MongoClient
+
+MAIN_OS_VARIABLE = json.loads(os.environ.get('config'))
+if MAIN_OS_VARIABLE is None:
+	sys.stderr.write("Configuration not found...")
+	sys.stderr.write("Exiting....")
+	sys.exit(1)
+
+MONGO_URI = MAIN_OS_VARIABLE.get('MONGO_URI')
+MONGO_SERVICE_DB = MAIN_OS_VARIABLE.get('MONGO_DB')
+MONGO_SERVICE_COLL = MAIN_OS_VARIABLE.get('MONGO_COLL')
+PASS_KEY = MAIN_OS_VARIABLE.get('PASS_KEY')
+
+MONGO_DB_OBJ = MongoClient(MONGO_URI)[MONGO_SERVICE_DB]
+
+HOST_CONFIG = MONGO_DB_OBJ[MONGO_SERVICE_COLL].find_one({'configId': 'hostConfig'}).get('config')
+APP_MONGO_COLLECTION = MONGO_DB_OBJ[MONGO_SERVICE_COLL].find_one({'configId': 'appMongoConfig'}).get('config')

scripts/common/constants.py

+class JanusDeploymentConstants:
+	JANUS_DEPLOYMENT_COLLECTION = "janusDeploymentConfigurations"
+	DEPLOYMENT_ID = 'deploymentId'
+	EXTRA_FIELDS_KEY = 'extra_fields'
+	LINE_COORDINATES = ['x1', 'y1', 'x2', 'y2']
+	COUNT_BAGS_FLAG = 'count_bags'
+	ALIGNMENT_KEY = 'alignment'
+	VERTICAL = 'vertical'
+	HORIZONTAL = 'horizontal'
+	MODEL_KEY = 'model'
+	DIRECTION_KEY = 'direction'
+	MRP_DETECT_KEY = 'mrp_detect'
+
+
+class CameraConstants:
+	videortpmap="VP8/90000"
+	videopt=96
+	threads=3
+	gStreamer = False
+	eventType = 'deploy'
+	created_by = 'user_6501'
+	event_status = 'pending'
+	deploymentTypeCreate = 'upgrade_and_deploy'
+	deploymentTypeRemove = 'remove'
+	pipeline_internal = {}
+	pipeline_category = "ai"
+	thread = 1
+	job_id = "pipeline_129"
+	deployment_key = 'deploymentId'
+	pipeline_deployment_type = 'docker'
+	docker_deployment_type = 'single'
+	command_eventtype = 'command'
+	command_type = 'docker'
+	restart_command = "restart_container"
+	stop_command = "stop_container"
+	start_command = "start_container"
+

scripts/loopbackmodel.py

+from edge_engine.ai.model.modelwraper import ModelWrapper
+import cv2
+import base64
+
+
+class LoopBackModel(ModelWrapper):
+
+    def __init__(self, pubs, path=None, ):
+        super().__init__(path)
+        self.mqtt = pubs.mqtt_pub
+
+    def _pre_process(self, x):
+        return x
+
+    def _post_process(self, x):
+        image = cv2.imencode('.jpg', x['frame'])[1].tostring()
+        image = 'data:image/jpeg;base64,' + base64.b64encode(image).decode("utf-8")
+        x['frame'] = image
+        self.mqtt.publish(x)
+        return x
+
+    def _predict(self, x):
+        return x
+
+    def predict(self, x):
+        return super().predict(x)

scripts/utils/centroidtracker.py

+# import the necessary packages
+from scipy.spatial import distance as dist
+from collections import OrderedDict
+import numpy as np
+from edge_engine.common.logsetup import logger
+
+
+class CentroidTracker():
+    def __init__(self, maxDisappeared=50):
+        # initialize the next unique object ID along with two ordered
+        # dictionaries used to keep track of mapping a given object
+        # ID to its centroid and number of consecutive frames it has
+        # been marked as "disappeared", respectively
+        self.nextObjectID = 0
+        self.objects = OrderedDict()
+        self.disappeared = OrderedDict()
+
+        # store the number of maximum consecutive frames a given
+        # object is allowed to be marked as "disappeared" until we
+        # need to deregister the object from tracking
+        self.maxDisappeared = maxDisappeared
+
+    def register(self, centroid):
+        # when registering an object we use the next available object
+        # ID to store the centroid
+        self.objects[self.nextObjectID] = {'has_print': False, 'centroid': centroid}
+        self.disappeared[self.nextObjectID] = 0
+        self.nextObjectID += 1
+
+    def deregister(self, objectID):
+        # to deregister an object ID we delete the object ID from
+        # both of our respective dictionaries
+        del self.objects[objectID]
+        del self.disappeared[objectID]
+
+    def update(self, rects):
+        # check to see if the list of input bounding box rectangles
+        # is empty
+        if len(rects) == 0:
+            # loop over any existing tracked objects and mark them
+            # as disappeared
+            for objectID in list(self.disappeared.keys()):
+                self.disappeared[objectID] += 1
+
+                # if we have reached a maximum number of consecutive
+                # frames where a given object has been marked as
+                # missing, deregister it
+                if self.disappeared[objectID] > self.maxDisappeared:
+                    self.deregister(objectID)
+
+            # return early as there are no centroids or tracking info
+            # to update
+            return self.objects
+
+        # initialize an array of input centroids for the current frame
+        inputCentroids = np.zeros((len(rects), 2), dtype="int")
+
+        # loop over the bounding box rectangles
+        for (i, (startX, startY, endX, endY)) in enumerate(rects):
+            # use the bounding box coordinates to derive the centroid
+            cX = int((startX + endX) / 2.0)
+            cY = int((startY + endY) / 2.0)
+            inputCentroids[i] = (cX, cY)
+
+        # if we are currently not tracking any objects take the input
+        # centroids and register each of them
+        if len(self.objects) == 0:
+            for i in range(0, len(inputCentroids)):
+                self.register(inputCentroids[i])
+
+        # otherwise, are are currently tracking objects so we need to
+        # try to match the input centroids to existing object
+        # centroids
+        else:
+            # grab the set of object IDs and corresponding centroids
+            objectIDs = list(self.objects.keys())
+            objectCentroids = [e['centroid'] for e in self.objects.values()]
+
+            # compute the distance between each pair of object
+            # centroids and input centroids, respectively -- our
+            # goal will be to match an input centroid to an existing
+            # object centroid
+            # logger.info(f"OBC --> {objectCentroids}")
+            try:
+                D = dist.cdist(np.array(objectCentroids), inputCentroids)
+            except Exception as e:
+                logger.info(f"objectCentroids --> {objectCentroids}")
+                logger.info(f"inputCentroids --> {inputCentroids}")
+                logger.exception(e)
+
+            # in order to perform this matching we must (1) find the
+            # smallest value in each row and then (2) sort the row
+            # indexes based on their minimum values so that the row
+            # with the smallest value as at the *front* of the index
+            # list
+            rows = D.min(axis=1).argsort()
+
+            # next, we perform a similar process on the columns by
+            # finding the smallest value in each column and then
+            # sorting using the previously computed row index list
+            cols = D.argmin(axis=1)[rows]
+
+            # in order to determine if we need to update, register,
+            # or deregister an object we need to keep track of which
+            # of the rows and column indexes we have already examined
+            usedRows = set()
+            usedCols = set()
+
+            # loop over the combination of the (row, column) index
+            # tuples
+            for (row, col) in zip(rows, cols):
+                # if we have already examined either the row or
+                # column value before, ignore it
+                # val
+                if row in usedRows or col in usedCols:
+                    continue
+
+                # otherwise, grab the object ID for the current row,
+                # set its new centroid, and reset the disappeared
+                # counter
+                objectID = objectIDs[row]
+                self.objects[objectID]['centroid'] = inputCentroids[col]
+                self.disappeared[objectID] = 0
+
+                # indicate that we have examined each of the row and
+                # column indexes, respectively
+                usedRows.add(row)
+                usedCols.add(col)
+
+            # compute both the row and column index we have NOT yet
+            # examined
+            unusedRows = set(range(0, D.shape[0])).difference(usedRows)
+            unusedCols = set(range(0, D.shape[1])).difference(usedCols)
+
+            # in the event that the number of object centroids is
+            # equal or greater than the number of input centroids
+            # we need to check and see if some of these objects have
+            # potentially disappeared
+            if D.shape[0] >= D.shape[1]:
+                # loop over the unused row indexes
+                for row in unusedRows:
+                    # grab the object ID for the corresponding row
+                    # index and increment the disappeared counter
+                    objectID = objectIDs[row]
+                    self.disappeared[objectID] += 1
+
+                    # check to see if the number of consecutive
+                    # frames the object has been marked "disappeared"
+                    # for warrants deregistering the object
+                    if self.disappeared[objectID] > self.maxDisappeared:
+                        self.deregister(objectID)
+
+            # otherwise, if the number of input centroids is greater
+            # than the number of existing object centroids we need to
+            # register each new input centroid as a trackable object
+            else:
+                for col in unusedCols:
+                    self.register(inputCentroids[col])
+
+        # return the set of trackable objects
+        return self.objects

scripts/utils/edge_utils.py

+from scripts.common.constants import JanusDeploymentConstants
+from scripts.common.config import MONGO_DB_OBJ, APP_MONGO_COLLECTION
+
+import cv2
+
+from edge_engine.common.logsetup import logger
+#from scripts.common.config import MONGO_DB_OBJ, APP_MONGO_COLLECTION
+#from scripts.common.constants import JanusDeploymentConstants
+
+
+class Utilities:
+
+    @classmethod
+    def get_extra_fields(
+            cls,
+            device_id,
+    ):
+        _janus_deployment = MONGO_DB_OBJ[
+            APP_MONGO_COLLECTION.get(JanusDeploymentConstants.JANUS_DEPLOYMENT_COLLECTION)].find_one(
+            {JanusDeploymentConstants.DEPLOYMENT_ID: device_id}).get(
+            JanusDeploymentConstants.EXTRA_FIELDS_KEY)
+        if _janus_deployment is None:
+            raise ValueError("Janus deployment configuration is not found/corrupted")
+
+        _key_dictionary = dict()
+        for each_field in _janus_deployment:
+            _key_dictionary[each_field['key']] = each_field['value']
+        return _key_dictionary
+
+    @classmethod
+    def get_direction(
+            cls,
+            device_id,
+    ):
+        logger.debug("Getting the direction from DB")
+        return MONGO_DB_OBJ[APP_MONGO_COLLECTION.get(JanusDeploymentConstants.JANUS_DEPLOYMENT_COLLECTION)].find_one(
+            {JanusDeploymentConstants.DEPLOYMENT_ID: device_id}).get(
+            JanusDeploymentConstants.DIRECTION_KEY)
+
+    @classmethod
+    def set_direction(
+            cls,
+            device_id: str,
+            direction: bool,
+    ):
+        logger.debug("Updating the direction in DB")
+        updated_values = {"$set": {JanusDeploymentConstants.DIRECTION_KEY: direction}}
+        MONGO_DB_OBJ[APP_MONGO_COLLECTION.get(JanusDeploymentConstants.JANUS_DEPLOYMENT_COLLECTION)].update_one(
+            {JanusDeploymentConstants.DEPLOYMENT_ID: device_id}, updated_values)
+
+    @classmethod
+    def draw_circles_on_frame(
+            cls,
+            frame,
+            point,
+            radius=3,
+            color=(255, 255, 255),
+            thickness=1,
+    ):
+        """
+        draw circle on the objects
+        :param radius: radius of the circle
+        :param frame: frame to draw on
+        :param point: co-ordinate to draw on
+        :param color: color of the circle
+        :param thickness: thickness of the circle
+        :return: frame
+        """
+        return cv2.circle(frame, tuple(point), radius, color, thickness)
+
+    @classmethod
+    def resize_to_64_64(
+            cls,
+            frame,
+    ):
+        """
+        resize the from
+        :param frame: frame
+        :return: frame
+        """
+        return cv2.resize(frame, (64, 64))
+
+
+def get_extra_fields(device_id):
+    # _janus_deployment = [
+    #     {
+    #         "type": "number",
+    #         "key": "x1",
+    #         "value": 1000
+    #     },
+    #     {
+    #         "type": "number",
+    #         "key": "y1",
+    #         "value": 0
+    #     },
+    #     {
+    #         "type": "number",
+    #         "key": "x2",
+    #         "value": 1001
+    #     },
+    #     {
+    #         "type": "number",
+    #         "key": "y2",
+    #         "value": 720
+    #     },
+    #     {
+    #         "type": "dropdown",
+    #         "key": "alignment",
+    #         "value": "vertical"
+    #     }
+    # ]
+    _janus_deployment = MONGO_DB_OBJ[APP_MONGO_COLLECTION.get(JanusDeploymentConstants.JANUS_DEPLOYMENT_COLLECTION)]. \
+        find_one({JanusDeploymentConstants.DEPLOYMENT_ID: device_id}).get(JanusDeploymentConstants.EXTRA_FIELDS_KEY)
+
+    if _janus_deployment is None:
+        raise ValueError("Janus deployment configuration is not found/corrupted")
+
+    _key_dictionary = dict()
+    for each_field in _janus_deployment:
+        _key_dictionary[each_field['key']] = each_field['value']
+    return _key_dictionary

scripts/utils/helpers.py

+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Jun 20 14:51:33 2017
+
+@author: kyleguan
+"""
+import numpy as np
+import cv2
+
+
+
+class Box:
+    def __init__(self):
+        self.x, self.y = float(), float()
+        self.w, self.h = float(), float()
+        self.c = float()
+        self.prob = float()
+
+
+def overlap(x1, w1, x2, w2):
+    l1 = x1 - w1 / 2.;
+    l2 = x2 - w2 / 2.;
+    left = max(l1, l2)
+    r1 = x1 + w1 / 2.;
+    r2 = x2 + w2 / 2.;
+    right = min(r1, r2)
+    return right - left;
+
+
+def box_intersection(a, b):
+    w = overlap(a.x, a.w, b.x, b.w);
+    h = overlap(a.y, a.h, b.y, b.h);
+    if w < 0 or h < 0: return 0;
+    area = w * h;
+    return area;
+
+
+def box_union(a, b):
+    i = box_intersection(a, b);
+    u = a.w * a.h + b.w * b.h - i;
+    return u;
+
+
+def box_iou(a, b):
+    return box_intersection(a, b) / box_union(a, b);
+
+
+def box_iou2(a, b):
+    '''
+    Helper funciton to calculate the ratio between intersection and the union of
+    two boxes a and b
+    a[0], a[1], a[2], a[3] <-> left, up, right, bottom
+    '''
+
+    w_intsec = np.maximum(0, (np.minimum(a[2], b[2]) - np.maximum(a[0], b[0])))
+    h_intsec = np.maximum(0, (np.minimum(a[3], b[3]) - np.maximum(a[1], b[1])))
+    s_intsec = w_intsec * h_intsec
+    s_a = (a[2] - a[0]) * (a[3] - a[1])
+    s_b = (b[2] - b[0]) * (b[3] - b[1])
+
+    return float(s_intsec) / (s_a + s_b - s_intsec)
+
+
+def convert_to_pixel(box_yolo, img, crop_range):
+    '''
+    Helper function to convert (scaled) coordinates of a bounding box
+    to pixel coordinates.
+
+    Example (0.89361443264143803, 0.4880486045564924, 0.23544462956491041,
+    0.36866588651069609)
+
+    crop_range: specifies the part of image to be cropped
+    '''
+
+    box = box_yolo
+    imgcv = img
+    [xmin, xmax] = crop_range[0]
+    [ymin, ymax] = crop_range[1]
+    h, w, _ = imgcv.shape
+
+    # Calculate left, top, width, and height of the bounding box
+    left = int((box.x - box.w / 2.) * (xmax - xmin) + xmin)
+    top = int((box.y - box.h / 2.) * (ymax - ymin) + ymin)
+
+    width = int(box.w * (xmax - xmin))
+    height = int(box.h * (ymax - ymin))
+
+    # Deal with corner cases
+    if left < 0:  left = 0
+    if top < 0:   top = 0
+
+    # Return the coordinates (in the unit of the pixels)
+
+    box_pixel = np.array([left, top, width, height])
+    return box_pixel
+
+
+def convert_to_cv2bbox(bbox, img_dim=(1280, 720)):
+    '''
+    Helper fucntion for converting bbox to bbox_cv2
+    bbox = [left, top, width, height]
+    bbox_cv2 = [left, top, right, bottom]
+    img_dim: dimension of the image, img_dim[0]<-> x
+    img_dim[1]<-> y
+    '''
+    left = np.maximum(0, bbox[0])
+    top = np.maximum(0, bbox[1])
+    right = np.minimum(img_dim[0], bbox[0] + bbox[2])
+    bottom = np.minimum(img_dim[1], bbox[1] + bbox[3])
+
+    return (left, top, right, bottom)
+
+
+def draw_box_label(id, img, bbox_cv2, box_color=(0, 255, 255), show_label=True):
+    '''
+    Helper funciton for drawing the bounding boxes and the labels
+    bbox_cv2 = [left, top, right, bottom]
+    '''
+    # box_color= (0, 255, 255)
+    font = cv2.FONT_HERSHEY_SIMPLEX
+    font_size = 0.7
+    font_color = (0, 0, 0)
+    left, top, right, bottom = bbox_cv2[1], bbox_cv2[0], bbox_cv2[3], bbox_cv2[2]
+
+    # Draw the bounding box
+    cv2.rectangle(img, (left, top), (right, bottom), box_color, 4)
+    # centroid = [int(left+((right - left)/2)), int(top+((bottom - top)/2))]
+    if show_label:
+        # Draw a filled box on top of the bounding box (as the background for the labels)
+        cv2.rectangle(img, (left - 2, top - 45), (right + 2, top), box_color, -1, 1)
+
+        # Output the labels that show the x and y coordinates of the bounding box center.
+        text_x = 'id=' + str(id)
+        cv2.putText(img, text_x, (left, top - 25), font, font_size, font_color, 1, cv2.LINE_AA)
+        text_y = 'y=' + str((top + bottom) / 2)
+        # cv2.putText(img, text_y, (left, top - 5), font, font_size, font_color, 1, cv2.LINE_AA)
+
+    return img

scripts/utils/ilens_request_handler.py

+import os
+
+import requests
+
+GENERATED_TOKEN_KEY = "model_container_pregenerated_token"
+LOGIN_TOKEN_KEY = "login-token"
+
+
+def delete(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.delete(**kwargs)
+
+
+def get(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.get(**kwargs)
+
+
+def head(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.head(**kwargs)
+
+
+def patch(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.patch(**kwargs)
+
+
+def post(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.post(**kwargs)
+
+
+def put(**kwargs):
+    if os.environ.get(GENERATED_TOKEN_KEY):
+        cookies = headers = {LOGIN_TOKEN_KEY: os.environ.get(GENERATED_TOKEN_KEY)}
+        kwargs.update(dict(cookies=cookies, headers=headers))
+    return requests.put(**kwargs)

scripts/utils/image_utils.py

+from edge_engine.common.logsetup import logger
+import cv2
+
+
+def draw_circles_on_frame(frame, point, radius=3, color=(255, 255, 255), thickness=1):
+    """
+    draw circle on the objects
+    :param radius: radius of the circle
+    :param frame: frame to draw on
+    :param point: co-ordinate to draw on
+    :param color: color of the circle
+    :param thickness: thickness of the circle
+    :return: frame
+    """
+    logger.debug("Drawing circle centroid on the frame")
+    return cv2.circle(frame, tuple(point), radius, color, thickness)
+
+
+def resize_to_64_64(frame):
+    """
+    resize the from
+    :param frame: frame
+    :return: frame
+    """
+    logger.debug("Resizing the frame to 64 x 64")
+    return cv2.resize(frame, (64, 64))
\ No newline at end of file

scripts/utils/infocenter.py

+import os
+from datetime import datetime
+
+# Security changes start
+# from requests import post
+from scripts.utils.ilens_request_handler import post
+# Security changes stop
+
+from uuid import uuid1
+from urllib.parse import urljoin
+from edge_engine.common.logsetup import logger
+from scripts.common.config import MONGO_DB_OBJ, APP_MONGO_COLLECTION
+
+
+class MongoLogger:
+    def __init__(self):
+        self.attendance_event_collection = MONGO_DB_OBJ[APP_MONGO_COLLECTION.get('eventLogCollection')]
+        self.camera_configuration = MONGO_DB_OBJ[APP_MONGO_COLLECTION.get('cameraConfigurationCollection')]
+        self.camera_mapping_json = self.get_all_cameras()
+
+    def get_all_cameras(self):
+        camera_mapping_json = self.camera_configuration.find({'decommissioned': False}, {"_id": 0})
+        camera_json = {}
+        for each in camera_mapping_json:
+            camera_json[each['cameraId']] = each['cameraName']
+        return camera_json
+
+    @staticmethod
+    def update_count_api(bag_type):
+        asset_id = os.environ.get('asset_id')
+        asset_hierarchy = os.environ.get('asset_hierarchy')
+        count_update_endpoint = os.environ.get('count_update_endpoint')
+        logger.debug("count_update_endpoint",count_update_endpoint)
+        if asset_id is not None and count_update_endpoint is not None and asset_hierarchy is not None:
+            response = post(url=count_update_endpoint,
+                            json=dict(asset_hierarchy=asset_hierarchy, count_increment=1, asset_id=asset_id,
+                                      bag_type=bag_type), timeout=5)
+            if response.status_code != 200:
+                logger.warning(
+                    "Value not updated in cards!. Invalid response from Update Count API: {}".format(response.content))
+        else:
+            logger.warning("Either asset_id, asset_hierarchy or count_update_endpoint is not set!."
+                           " Not updating the cards API!")
+
+    def insert_attendance_event_to_mongo(self, data):
+        try:
+            input_data = {
+                "eventId": str(uuid1()).split('-')[0],
+                "cameraId": data['deviceId'],
+                "cameraName": self.camera_mapping_json.get(data['deviceId'], "Thermal Camera"),
+                "timestamp": datetime.now(),
+                "frame": data['frame'],
+                "eventtype": "Intrusion Detection",
+                "bg_color": data["bg_color"],
+                "font_color": data["font_color"],
+                "intrusion_message": data["message"],
+                "alert_sound": data["alert_sound"],
+                "logged_activity": data["activity"],
+                "mrp_frmae": data["mrp_frmae"],
+                "mrp_roi": data["mrp_roi"]}
+            if os.environ.get('app') is not None:
+                input_data['app'] = os.environ.get('app')
+
+            logger.info("Pushing to Mongo..")
+            self.attendance_event_collection.insert_one(input_data)
+            self.update_count_api(data["bag_type"])
+        except Exception as e:
+            logger.exception(e)
+
+    def get_camera_details(self, camera_id):
+        camera_details_json = self.camera_configuration.find_one({"cameraId": camera_id})
+        return camera_details_json

scripts/utils/model_tracker.py

+from datetime import datetime
+
+from scripts.common.config import MONGO_DB_OBJ
+
+
+class ModelCountTracker:
+    def __init__(
+            self,
+            device_id,
+    ) -> None:
+        self.device_id = device_id
+        self.count_tracker = None
+        self._reset_tracker()
+
+    def _reset_tracker(self):
+        self.count_tracker = list()
+
+    def __call__(
+            self,
+            conf: float,
+    ) -> None:
+        self.count_tracker.append(
+            {
+                "time": datetime.now(),
+                "deviceId": self.device_id,
+                "count_confidence": conf
+            })
+        if len(self.count_tracker) >= 10:
+            self.insert_to_mongo(self.count_tracker)
+            self._reset_tracker()
+
+    @staticmethod
+    def insert_to_mongo(
+            payload: list,
+            collection_name: str = "model_count_tracker"
+    ) -> None:
+        MONGO_DB_OBJ[collection_name].insert_many(payload)
+
+
+class ModelTracker:
+    def __init__(
+            self,
+            device_id,
+    ) -> None:
+        self.device_id = device_id
+        self.model_tracker = None
+        self._reset_tracker()
+
+    def _reset_tracker(self):
+        self.model_tracker = list()
+
+    def __call__(
+            self,
+            conf: float,
+    ) -> None:
+        self.model_tracker.append(
+            {
+                "time": datetime.now(),
+                "deviceId": self.device_id,
+                "model_confidence": conf
+            })
+        if len(self.model_tracker) >= 500:
+            self.insert_to_mongo(self.model_tracker)
+            self._reset_tracker()
+
+    @staticmethod
+    def insert_to_mongo(
+            payload: list,
+            collection_name: str = "model_confidence_tracker"
+    ) -> None:
+        MONGO_DB_OBJ[collection_name].insert_many(payload)

scripts/utils/relay_util.py

+import time
+import requests
+from edge_engine.common.logsetup import logger
+
+
+class RelayHandler:
+
+    @staticmethod
+    def update_relay_status(
+            ep: str,
+            payload: dict,
+    ) -> None:
+        logger.debug("Updating the relay status to : {}".format(payload))
+        response = None
+        for _ in range(0, 3):
+            response = requests.post(url=ep, json=payload, timeout=10)
+            if response.status_code == 200 and response.json().get('status'):
+                return
+            time.sleep(1)
+
+        logger.error("Unable to update the relay status. Error: {}".format(response.content))
+        raise RuntimeError("Unable to communicate to belt relay!")
\ No newline at end of file

scripts/utils/tracker.py

+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+import numpy as np
+from numpy import dot
+from scipy.linalg import inv, block_diag
+
+
+class Tracker():  # class for Kalman Filter based tracker
+    def __init__(self):
+        # Initialize parametes for tracker (history)
+        self.id = 0  # tracker's id
+        self.box = []  # list to store the coordinates for a bounding box
+        self.hits = 0  # number of detection matches
+        self.no_losses = 0  # number of unmatched tracks (track loss)
+
+        # Initialize parameters for Kalman Filtering
+        # The state is the (x, y) coordinates of the detection box
+        # state: [up, up_dot, left, left_dot, down, down_dot, right, right_dot]
+        # or[up, up_dot, left, left_dot, height, height_dot, width, width_dot]
+        self.x_state = []
+        self.dt = 1.  # time interval
+
+        # Process matrix, assuming constant velocity model
+        self.F = np.array([[1, self.dt, 0, 0, 0, 0, 0, 0],
+                           [0, 1, 0, 0, 0, 0, 0, 0],
+                           [0, 0, 1, self.dt, 0, 0, 0, 0],
+                           [0, 0, 0, 1, 0, 0, 0, 0],
+                           [0, 0, 0, 0, 1, self.dt, 0, 0],
+                           [0, 0, 0, 0, 0, 1, 0, 0],
+                           [0, 0, 0, 0, 0, 0, 1, self.dt],
+                           [0, 0, 0, 0, 0, 0, 0, 1]])
+
+        # Measurement matrix, assuming we can only measure the coordinates
+
+        self.H = np.array([[1, 0, 0, 0, 0, 0, 0, 0],
+                           [0, 0, 1, 0, 0, 0, 0, 0],
+                           [0, 0, 0, 0, 1, 0, 0, 0],
+                           [0, 0, 0, 0, 0, 0, 1, 0]])
+
+        # Initialize the state covariance
+        self.L = 100.0
+        self.P = np.diag(self.L * np.ones(8))
+
+        # Initialize the process covariance
+        self.Q_comp_mat = np.array([[self.dt ** 4 / 2., self.dt ** 3 / 2.],
+                                    [self.dt ** 3 / 2., self.dt ** 2]])
+        self.Q = block_diag(self.Q_comp_mat, self.Q_comp_mat,
+                            self.Q_comp_mat, self.Q_comp_mat)
+
+        # Initialize the measurement covariance
+        self.R_ratio = 1.0 / 16.0
+        self.R_diag_array = self.R_ratio * np.array([self.L, self.L, self.L, self.L])
+        self.R = np.diag(self.R_diag_array)
+
+    def update_R(self):
+        R_diag_array = self.R_ratio * np.array([self.L, self.L, self.L, self.L])
+        self.R = np.diag(R_diag_array)
+
+    def kalman_filter(self, z):
+        '''
+        Implement the Kalman Filter, including the predict and the update stages,
+        with the measurement z
+        '''
+        x = self.x_state
+        # Predict
+        x = dot(self.F, x)
+        self.P = dot(self.F, self.P).dot(self.F.T) + self.Q
+
+        # Update
+        S = dot(self.H, self.P).dot(self.H.T) + self.R
+        K = dot(self.P, self.H.T).dot(inv(S))  # Kalman gain
+        y = z - dot(self.H, x)  # residual
+        x += dot(K, y)
+        self.P = self.P - dot(K, self.H).dot(self.P)
+        self.x_state = x.astype(int)  # convert to integer coordinates
+        # (pixel values)
+
+    def predict_only(self):
+        '''
+        Implment only the predict stage. This is used for unmatched detections and
+        unmatched tracks
+        '''
+        x = self.x_state
+        # Predict
+        x = dot(self.F, x)
+        self.P = dot(self.F, self.P).dot(self.F.T) + self.Q
+        self.x_state = x.astype(int)
+
+
+if __name__ == "__main__":
+    import matplotlib.pyplot as plt
+    import glob
+    import helpers
+
+    # Creat an instance
+    trk = Tracker()
+    # Test R_ratio
+    trk.R_ratio = 1.0 / 16
+    # Update measurement noise covariance matrix
+    trk.update_R()
+    # Initial state
+    x_init = np.array([390, 0, 1050, 0, 513, 0, 1278, 0])
+    x_init_box = [x_init[0], x_init[2], x_init[4], x_init[6]]
+    # Measurement
+    z = np.array([399, 1022, 504, 1256])
+    trk.x_state = x_init.T
+    trk.kalman_filter(z.T)
+    # Updated state
+    x_update = trk.x_state
+    x_updated_box = [x_update[0], x_update[2], x_update[4], x_update[6]]
+
+    print('The initial state is: ', x_init)
+    print('The measurement is: ', z)
+    print('The update state is: ', x_update)
+
+    # Visualize the Kalman filter process and the
+    # impact of measurement nosie convariance matrix
+
+    images = [plt.imread(file) for file in glob.glob('./test_images/*.jpg')]
+    img = images[3]
+
+    plt.figure(figsize=(10, 14))
+    helpers.draw_box_label(img, x_init_box, box_color=(0, 255, 0))
+    ax = plt.subplot(3, 1, 1)
+    plt.imshow(img)
+    plt.title('Initial: ' + str(x_init_box))
+
+    helpers.draw_box_label(img, z, box_color=(255, 0, 0))
+    ax = plt.subplot(3, 1, 2)
+    plt.imshow(img)
+    plt.title('Measurement: ' + str(z))
+
+    helpers.draw_box_label(img, x_updated_box)
+    ax = plt.subplot(3, 1, 3)
+    plt.imshow(img)
+    plt.title('Updated: ' + str(x_updated_box))
+    plt.show()

scripts/utils/yolov5_trt.py

+import ctypes
+import time
+import cv2
+import numpy as np
+import pycuda.autoinit
+import pycuda.driver as cuda
+import tensorrt as trt
+
+PLUGIN_LIBRARY = "/home/ilens/container_weights/libmyplugins.so"
+
+ctypes.CDLL(PLUGIN_LIBRARY)
+
+
+class YoloV5TRT(object):
+    """
+    description: A YOLOv5 class that warps TensorRT ops, preprocess and postprocess ops.
+    """
+
+    def __init__(self, engine_file_path, conf_thresh, iou_thresh):
+        self.CONF_THRESH = conf_thresh
+        self.IOU_THRESHOLD = iou_thresh
+        self.ctx = cuda.Device(0).make_context()
+        stream = cuda.Stream()
+        TRT_LOGGER = trt.Logger(trt.Logger.INFO)
+        runtime = trt.Runtime(TRT_LOGGER)
+
+        with open(engine_file_path, "rb") as f:
+            engine = runtime.deserialize_cuda_engine(f.read())
+        context = engine.create_execution_context()
+
+        host_inputs = []
+        cuda_inputs = []
+        host_outputs = []
+        cuda_outputs = []
+        bindings = []
+
+        for binding in engine:
+            size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
+            dtype = trt.nptype(engine.get_binding_dtype(binding))
+
+            host_mem = cuda.pagelocked_empty(size, dtype)
+            cuda_mem = cuda.mem_alloc(host_mem.nbytes)
+
+            bindings.append(int(cuda_mem))
+
+            if engine.binding_is_input(binding):
+                self.input_w = engine.get_binding_shape(binding)[-1]
+                self.input_h = engine.get_binding_shape(binding)[-2]
+                host_inputs.append(host_mem)
+                cuda_inputs.append(cuda_mem)
+            else:
+                host_outputs.append(host_mem)
+                cuda_outputs.append(cuda_mem)
+
+        self.stream = stream
+        self.context = context
+        self.engine = engine
+        self.host_inputs = host_inputs
+        self.cuda_inputs = cuda_inputs
+        self.host_outputs = host_outputs
+        self.cuda_outputs = cuda_outputs
+        self.bindings = bindings
+        self.batch_size = engine.max_batch_size
+
+    def infer(self, frame):
+
+        self.ctx.push()
+
+        stream = self.stream
+        context = self.context
+        engine = self.engine
+        host_inputs = self.host_inputs
+        cuda_inputs = self.cuda_inputs
+        host_outputs = self.host_outputs
+        cuda_outputs = self.cuda_outputs
+        bindings = self.bindings
+
+        input_image, image_raw, origin_h, origin_w = self.preprocess_image(frame)
+
+        np.copyto(host_inputs[0], input_image.ravel())
+        start = time.time()
+
+        cuda.memcpy_htod_async(cuda_inputs[0], host_inputs[0], stream)
+
+        context.execute_async(batch_size=self.batch_size, bindings=bindings, stream_handle=stream.handle)
+
+        cuda.memcpy_dtoh_async(host_outputs[0], cuda_outputs[0], stream)
+
+        stream.synchronize()
+
+        self.ctx.pop()
+
+        output = host_outputs[0]
+
+        result_boxes, result_scores, result_classid = [], [], []
+        for i in range(self.batch_size):
+            result_boxes, result_scores, result_classid = self.post_process(
+                output[i * 6001: (i + 1) * 6001], frame.shape[0], frame.shape[1])
+
+            # if len(result_boxes) > 0:
+            #     for i in range(len(result_boxes)):
+            #         print("Result -->", result_boxes[i])
+            #         print("Scores -->", result_scores[i])
+            #         print("Class ID -->", result_classid[i])
+        # result_boxes = list(map(int, result_boxes))
+        return result_boxes, result_scores, result_classid
+
+    def destroy(self):
+        self.ctx.pop()
+
+    def preprocess_image(self, raw_bgr_image):
+        """
+        description: Convert BGR image to RGB,
+                  resize and pad it to target size, normalize to [0,1],
+                  transform to NCHW format.
+        param:
+           input_image_path: str, image path
+        return:
+           image:  the processed image
+           image_raw: the original image
+           h: original height
+           w: original width
+        """
+        image_raw = raw_bgr_image
+        h, w, c = image_raw.shape
+        image = cv2.cvtColor(image_raw, cv2.COLOR_BGR2RGB)
+
+        r_w = self.input_w / w
+        r_h = self.input_h / h
+        if r_h > r_w:
+            tw = self.input_w
+            th = int(r_w * h)
+            tx1 = tx2 = 0
+            ty1 = int((self.input_h - th) / 2)
+            ty2 = self.input_h - th - ty1
+        else:
+            tw = int(r_h * w)
+            th = self.input_h
+            tx1 = int((self.input_w - tw) / 2)
+            tx2 = self.input_w - tw - tx1
+            ty1 = ty2 = 0
+
+        image = cv2.resize(image, (tw, th))
+
+        image = cv2.copyMakeBorder(
+            image, ty1, ty2, tx1, tx2, cv2.BORDER_CONSTANT, (128, 128, 128)
+        )
+        image = image.astype(np.float32)
+
+        image /= 255.0
+
+        image = np.transpose(image, [2, 0, 1])
+
+        image = np.expand_dims(image, axis=0)
+
+        image = np.ascontiguousarray(image)
+        return image, image_raw, h, w
+
+    def xywh2xyxy(self, origin_h, origin_w, x):
+        """
+        description:    Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+        param:
+           origin_h:   height of original image
+           origin_w:   width of original image
+           x:          A boxes numpy, each row is a box [center_x, center_y, w, h]
+        return:
+           y:          A boxes numpy, each row is a box [x1, y1, x2, y2]
+        """
+        y = np.zeros_like(x)
+        r_w = self.input_w / origin_w
+        r_h = self.input_h / origin_h
+        if r_h > r_w:
+            y[:, 0] = x[:, 0] - x[:, 2] / 2
+            y[:, 2] = x[:, 0] + x[:, 2] / 2
+            y[:, 1] = x[:, 1] - x[:, 3] / 2 - (self.input_h - r_w * origin_h) / 2
+            y[:, 3] = x[:, 1] + x[:, 3] / 2 - (self.input_h - r_w * origin_h) / 2
+            y /= r_w
+        else:
+            y[:, 0] = x[:, 0] - x[:, 2] / 2 - (self.input_w - r_h * origin_w) / 2
+            y[:, 2] = x[:, 0] + x[:, 2] / 2 - (self.input_w - r_h * origin_w) / 2
+            y[:, 1] = x[:, 1] - x[:, 3] / 2
+            y[:, 3] = x[:, 1] + x[:, 3] / 2
+            y /= r_h
+
+        return y
+
+    def post_process(self, output, origin_h, origin_w):
+        """
+        description: postprocess the prediction
+        param:
+           output:     A numpy likes [num_boxes,cx,cy,w,h,conf,cls_id, cx,cy,w,h,conf,cls_id, ...]
+           origin_h:   height of original image
+           origin_w:   width of original image
+        return:
+           result_boxes: finally boxes, a boxes numpy, each row is a box [x1, y1, x2, y2]
+           result_scores: finally scores, a numpy, each element is the score correspoing to box
+           result_classid: finally classid, a numpy, each element is the classid correspoing to box
+        """
+
+        num = int(output[0])
+
+        pred = np.reshape(output[1:], (-1, 6))[:num, :]
+
+        boxes = self.non_max_suppression(pred, origin_h, origin_w, conf_thres=self.CONF_THRESH,
+                                         nms_thres=self.IOU_THRESHOLD)
+        result_boxes = boxes[:, :4].astype(int) if len(boxes) else np.array([])
+        result_scores = boxes[:, 4] if len(boxes) else np.array([])
+        result_classid = boxes[:, 5].astype(int) if len(boxes) else np.array([])
+        return result_boxes, result_scores, result_classid
+
+    def bbox_iou(self, box1, box2, x1y1x2y2=True):
+        """
+        description: compute the IoU of two bounding boxes
+        param:
+           box1: A box coordinate (can be (x1, y1, x2, y2) or (x, y, w, h))
+           box2: A box coordinate (can be (x1, y1, x2, y2) or (x, y, w, h))
+           x1y1x2y2: select the coordinate format
+        return:
+           iou: computed iou
+        """
+        if not x1y1x2y2:
+
+            b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
+            b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
+            b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
+            b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2
+        else:
+
+            b1_x1, b1_y1, b1_x2, b1_y2 = box1[:, 0], box1[:, 1], box1[:, 2], box1[:, 3]
+            b2_x1, b2_y1, b2_x2, b2_y2 = box2[:, 0], box2[:, 1], box2[:, 2], box2[:, 3]
+
+        inter_rect_x1 = np.maximum(b1_x1, b2_x1)
+        inter_rect_y1 = np.maximum(b1_y1, b2_y1)
+        inter_rect_x2 = np.minimum(b1_x2, b2_x2)
+        inter_rect_y2 = np.minimum(b1_y2, b2_y2)
+
+        inter_area = np.clip(inter_rect_x2 - inter_rect_x1 + 1, 0, None) * \
+                     np.clip(inter_rect_y2 - inter_rect_y1 + 1, 0, None)
+
+        b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
+        b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)
+
+        iou = inter_area / (b1_area + b2_area - inter_area + 1e-16)
+
+        return iou
+
+    def non_max_suppression(self, prediction, origin_h, origin_w, conf_thres=0.5, nms_thres=0.4):
+        """
+        description: Removes detections with lower object confidence score than 'conf_thres' and performs
+        Non-Maximum Suppression to further filter detections.
+        param:
+           prediction: detections, (x1, y1, x2, y2, conf, cls_id)
+           origin_h: original image height
+           origin_w: original image width
+           conf_thres: a confidence threshold to filter detections
+           nms_thres: a iou threshold to filter detections
+        return:
+           boxes: output after nms with the shape (x1, y1, x2, y2, conf, cls_id)
+        """
+
+        boxes = prediction[prediction[:, 4] >= conf_thres]
+
+        boxes[:, :4] = self.xywh2xyxy(origin_h, origin_w, boxes[:, :4])
+
+        boxes[:, 0] = np.clip(boxes[:, 0], 0, origin_w - 1)
+        boxes[:, 2] = np.clip(boxes[:, 2], 0, origin_w - 1)
+        boxes[:, 1] = np.clip(boxes[:, 1], 0, origin_h - 1)
+        boxes[:, 3] = np.clip(boxes[:, 3], 0, origin_h - 1)
+
+        confs = boxes[:, 4]
+
+        boxes = boxes[np.argsort(-confs)]
+
+        keep_boxes = []
+        while boxes.shape[0]:
+            large_overlap = self.bbox_iou(np.expand_dims(boxes[0, :4], 0), boxes[:, :4]) > nms_thres
+            label_match = boxes[0, -1] == boxes[:, -1]
+
+            invalid = large_overlap & label_match
+            keep_boxes += [boxes[0]]
+            boxes = boxes[~invalid]
+        boxes = np.stack(keep_boxes, 0) if len(keep_boxes) else np.array([])
+        return boxes
+
+
+class inferThread():
+    def __init__(self, yolov5_wrapper):
+        self.yolov5_wrapper = yolov5_wrapper
+
+    def run(self):
+        cap = cv2.VideoCapture("test2.mp4")
+        ret, frame = cap.read()
+        while ret:
+            result_boxes, result_scores, result_classid = self.yolov5_wrapper.infer(frame)
+            out = [{"points": list(points), "conf": conf, "class": class_id} for points, conf, class_id in
+                   zip(result_boxes, result_scores, result_classid)]
+            print(out)
+            ret, frame = cap.read()
+
+
+if __name__ == "__main__":
+
+    engine_file_path = "build/yolov5.engine"
+
+    categories = ["cement_bag"]
+
+    yolov5_wrapper = YoloV5TRT(engine_file_path)
+    try:
+        inf = inferThread(yolov5_wrapper)
+        inf.run()
+    finally:
+        yolov5_wrapper.destroy()

test_typer.py

+black_white_ratio_dict = {'ambuja_plus': 1.2, 'acc_gold': 1.2, 'acc_suraksha_power_plus': 1.2, 'ambuja_buildcem': 1.2, 'acc_suraksha_power': 1.2, 'acc_nfr': 1.2, 'acc_concrete_plus': 1.2}
+
+
+lack_white_ratio = black_white_ratio_dict["{class_name}".format(class_name="ambuja_plus")]
+print(lack_white_ratio)
\ No newline at end of file

tests/test_CementBagCounter.py

+from os import environ
+
+environ["config"] = '{"MONGO_URI": "mongodb://admin:iLens!8989@192.168.0.220:21017", "MONGO_DATABASE": "ilens_wps", ' \
+                    '"MONGO_DB": "ilens_wps","MONGO_COLLECTION": "janusDeployment", "MONGO_KEY": "deploymentId", ' \
+                    '"MONGO_VALUE": "1b180a0e", "MONGO_SERVICE_COLL": "serviceConfiguration", "MONGO_COLL": ' \
+                    '"serviceConfiguration"  } '
+import unittest
+
+from edge_engine.edge_processor import Pubs
+from edge_engine.common.config import EDGE_CONFIG
+from scripts.cement_counter import CementBagCounter
+
+
+class TestCementBagCounter(unittest.TestCase):
+
+    def test__pre_process(self):
+        self.assertEqual(CementBagCounter(config=EDGE_CONFIG, model_config=EDGE_CONFIG["modelConfig"], pubs=Pubs(),
+                                          device_id=EDGE_CONFIG['deviceId'])._pre_process("5"), '5')

yolov5processor/infer.py

+import torch
+import numpy as np
+from numpy import random
+
+from yolov5processor.models.experimental import attempt_load
+from yolov5processor.utils.datasets import letterbox
+from yolov5processor.utils.general import (check_img_size, non_max_suppression, scale_coords)
+from yolov5processor.utils.torch_utils import select_device
+
+
+class ExecuteInference:
+    def __init__(self, weight, confidence=0.4, img_size=640, agnostic_nms=False, gpu=False, iou=0.5):
+        self.weight = weight
+        self.confidence = confidence
+        self.gpu = gpu
+        self.iou = iou
+        self.agnostic_nms = agnostic_nms
+        self.img_size = img_size
+        self.device, self.half = self.inference_device()
+        self.classes, self.model, self.names, self.colors = self.load_model()
+        print("Loaded Models...")
+
+    def inference_device(self):
+        if self.gpu:
+            device = select_device(str(torch.cuda.current_device()))
+            print("Using GPU Resource(s): {}".format(str(torch.cuda.current_device())))
+        else:
+            device = select_device('cpu')
+            print("Using CPU Resources")
+        half = device.type != 'cpu'
+        return device, half
+
+    def load_model(self):
+        model = attempt_load(self.weight, map_location=self.device)
+        imgsz = check_img_size(self.img_size, s=model.stride.max())
+        if self.half:
+            model.half()
+        names = model.module.names if hasattr(model, 'module') else model.names
+        print("Yolo v5 Model Classes: {}".format(names))
+        colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))]
+        img = torch.zeros((1, 3, imgsz, imgsz), device=self.device)
+        _ = model(img.half() if self.half else img) if self.device.type != 'cpu' else None
+        class_map = {index: label for index, label in zip(range(len(names)), names)}
+        return class_map, model, names, colors
+
+    def predict(self, image):
+        img = letterbox(image, new_shape=self.img_size)[0]
+        img = img[:, :, ::-1].transpose(2, 0, 1)
+        img = np.ascontiguousarray(img)
+        img = torch.from_numpy(img).to(self.device)
+        img = img.half() if self.half else img.float()
+        img /= 255.0
+        if img.ndimension() == 3:
+            img = img.unsqueeze(0)
+        pred = self.model(img, augment=False)[0]
+        pred = non_max_suppression(pred, self.confidence, self.iou, classes=None, agnostic=self.agnostic_nms)
+        _output = list()
+        for i, det in enumerate(pred):
+            if det is not None and len(det):
+                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], image.shape).round()
+                for *xyxy, conf, cls in reversed(det):
+                    _output.append({"points": [int(each) for each in xyxy],
+                                    "conf": round(float(conf), 4),
+                                    "class": self.classes[int(cls)]})
+        return _output

yolov5processor/models/common.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Common modules
+"""
+
+import logging
+import math
+import warnings
+from copy import copy
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image
+from torch.cuda import amp
+
+from yolov5processor.utils.datasets import exif_transpose, letterbox
+from yolov5processor.utils.general import colorstr, increment_path, make_divisible, non_max_suppression, save_one_box, \
+    scale_coords, xyxy2xywh
+from yolov5processor.utils.plots import Annotator, colors
+from yolov5processor.utils.torch_utils import time_sync
+
+LOGGER = logging.getLogger(__name__)
+
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def forward_fuse(self, x):
+        return self.act(self.conv(x))
+
+
+class DWConv(Conv):
+    # Depth-wise convolution class
+    def __init__(self, c1, c2, k=1, s=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2).unsqueeze(0).transpose(0, 3).squeeze(3)
+        return self.tr(p + self.linear(p)).unsqueeze(3).transpose(0, 3).reshape(b, self.c2, w, h)
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class C3TR(C3):
+    # C3 module with TransformerBlock()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class C3SPP(C3):
+    # C3 module with SPP()
+    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = SPP(c_, c_, k)
+
+
+class C3Ghost(C3):
+    # C3 module with GhostBottleneck()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[GhostBottleneck(c_, c_) for _ in range(n)])
+
+
+class SPP(nn.Module):
+    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            y1 = self.m(x)
+            y2 = self.m(y1)
+            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+        # return self.conv(self.contract(x))
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super().__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat([y, self.cv2(y)], 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super().__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
+                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, s, s, c // s ** 2, h, w)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(b, c // s ** 2, h * s, w * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super().__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class AutoShape(nn.Module):
+    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    classes = None  # (optional list) filter by class
+    multi_label = False  # NMS multiple labels per box
+    max_det = 1000  # maximum number of detections per image
+
+    def __init__(self, model):
+        super().__init__()
+        self.model = model.eval()
+
+    def autoshape(self):
+        LOGGER.info('AutoShape already enabled, skipping... ')  # model already converted to model.autoshape()
+        return self
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        m = self.model.model[-1]  # Detect()
+        m.stride = fn(m.stride)
+        m.grid = list(map(fn, m.grid))
+        if isinstance(m.anchor_grid, list):
+            m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+    @torch.no_grad()
+    def forward(self, imgs, size=640, augment=False, profile=False):
+        # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
+        #   file:       imgs = 'data/images/zidane.jpg'  # str or PosixPath
+        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        t = [time_sync()]
+        p = next(self.model.parameters())  # for device and type
+        if isinstance(imgs, torch.Tensor):  # torch
+            with amp.autocast(enabled=p.device.type != 'cpu'):
+                return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
+
+        # Pre-process
+        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
+        shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+        for i, im in enumerate(imgs):
+            f = f'image{i}'  # filename
+            if isinstance(im, (str, Path)):  # filename or uri
+                im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
+                im = np.asarray(exif_transpose(im))
+            elif isinstance(im, Image.Image):  # PIL Image
+                im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
+            files.append(Path(f).with_suffix('.jpg').name)
+            if im.shape[0] < 5:  # image in CHW
+                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+            im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3)  # enforce 3ch input
+            s = im.shape[:2]  # HWC
+            shape0.append(s)  # image shape
+            g = (size / max(s))  # gain
+            shape1.append([y * g for y in s])
+            imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
+        shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)]  # inference shape
+        x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs]  # pad
+        x = np.stack(x, 0) if n > 1 else x[0][None]  # stack
+        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
+        x = torch.from_numpy(x).to(p.device).type_as(p) / 255.  # uint8 to fp16/32
+        t.append(time_sync())
+
+        with amp.autocast(enabled=p.device.type != 'cpu'):
+            # Inference
+            y = self.model(x, augment, profile)[0]  # forward
+            t.append(time_sync())
+
+            # Post-process
+            y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes,
+                                    multi_label=self.multi_label, max_det=self.max_det)  # NMS
+            for i in range(n):
+                scale_coords(shape1, y[i][:, :4], shape0[i])
+
+            t.append(time_sync())
+            return Detections(imgs, y, files, t, self.names, x.shape)
+
+
+class Detections:
+    # YOLOv5 detections class for inference results
+    def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
+        super().__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
+        self.imgs = imgs  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3))  # timestamps (ms)
+        self.s = shape  # inference BCHW shape
+
+    def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
+        crops = []
+        for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
+            s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
+            if pred.shape[0]:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                if show or save or render or crop:
+                    annotator = Annotator(im, example=str(self.names))
+                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        if crop:
+                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
+                            crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
+                                          'im': save_one_box(box, im, file=file, save=save)})
+                        else:  # all others
+                            annotator.box_label(box, label, color=colors(cls))
+                    im = annotator.im
+            else:
+                s += '(no detections)'
+
+            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
+            if pprint:
+                LOGGER.info(s.rstrip(', '))
+            if show:
+                im.show(self.files[i])  # show
+            if save:
+                f = self.files[i]
+                im.save(save_dir / f)  # save
+                if i == self.n - 1:
+                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
+            if render:
+                self.imgs[i] = np.asarray(im)
+        if crop:
+            if save:
+                LOGGER.info(f'Saved results to {save_dir}\n')
+            return crops
+
+    def print(self):
+        self.display(pprint=True)  # print results
+        LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
+                    self.t)
+
+    def show(self):
+        self.display(show=True)  # show results
+
+    def save(self, save_dir='runs/detect/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True)  # increment save_dir
+        self.display(save=True, save_dir=save_dir)  # save results
+
+    def crop(self, save=True, save_dir='runs/detect/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
+        return self.display(crop=True, save=save, save_dir=save_dir)  # crop results
+
+    def render(self):
+        self.display(render=True)  # render results
+        return self.imgs
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
+        for d in x:
+            for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+                setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def __len__(self):
+        return self.n
+
+
+class Classify(nn.Module):
+    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
+        self.flat = nn.Flatten()
+
+    def forward(self, x):
+        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
+        return self.flat(self.conv(z))  # flatten to x(b,c2)

yolov5processor/models/experimental.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Experimental modules
+"""
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from yolov5processor.models.common import Conv
+from yolov5processor.utils.downloads import attempt_download
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super().__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
+        super().__init__()
+        groups = len(k)
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, groups - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(groups)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * groups
+            a = np.eye(groups + 1, groups, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+
+    def forward(self, x):
+        return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        y = []
+        for module in self:
+            y.append(module(x, augment, profile, visualize)[0])
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, map_location=None, inplace=True, fuse=True):
+    from yolov5processor.models.yolo import Detect, Model
+
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        ckpt = torch.load(attempt_download(w), map_location=map_location)  # load
+        if fuse:
+            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model
+        else:
+            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval())  # without layer fuse
+
+
+    # Compatibility updates
+    for m in model.modules():
+        if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
+            m.inplace = inplace  # pytorch 1.7.0 compatibility
+            if type(m) is Detect:
+                if not isinstance(m.anchor_grid, list):  # new Detect Layer compatibility
+                    delattr(m, 'anchor_grid')
+                    setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
+        elif type(m) is Conv:
+            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print(f'Ensemble created with {weights}\n')
+        for k in ['names']:
+            setattr(model, k, getattr(model[-1], k))
+        model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
+        return model  # return ensemble

yolov5processor/models/hub/anchors.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+# Default anchors for COCO data
+
+
+# P5 -------------------------------------------------------------------------------------------------------------------
+# P5-640:
+anchors_p5_640:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+
+# P6 -------------------------------------------------------------------------------------------------------------------
+# P6-640:  thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11,  21,19,  17,41,  43,32,  39,70,  86,64,  65,131,  134,130,  120,265,  282,180,  247,354,  512,387
+anchors_p6_640:
+  - [9,11,  21,19,  17,41]  # P3/8
+  - [43,32,  39,70,  86,64]  # P4/16
+  - [65,131,  134,130,  120,265]  # P5/32
+  - [282,180,  247,354,  512,387]  # P6/64
+
+# P6-1280:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27,  44,40,  38,94,  96,68,  86,152,  180,137,  140,301,  303,264,  238,542,  436,615,  739,380,  925,792
+anchors_p6_1280:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# P6-1920:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41,  67,59,  57,141,  144,103,  129,227,  270,205,  209,452,  455,396,  358,812,  653,922,  1109,570,  1387,1187
+anchors_p6_1920:
+  - [28,41,  67,59,  57,141]  # P3/8
+  - [144,103,  129,227,  270,205]  # P4/16
+  - [209,452,  455,396,  358,812]  # P5/32
+  - [653,922,  1109,570,  1387,1187]  # P6/64
+
+
+# P7 -------------------------------------------------------------------------------------------------------------------
+# P7-640:  thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11,  13,30,  29,20,  30,46,  61,38,  39,92,  78,80,  146,66,  79,163,  149,150,  321,143,  157,303,  257,402,  359,290,  524,372
+anchors_p7_640:
+  - [11,11,  13,30,  29,20]  # P3/8
+  - [30,46,  61,38,  39,92]  # P4/16
+  - [78,80,  146,66,  79,163]  # P5/32
+  - [149,150,  321,143,  157,303]  # P6/64
+  - [257,402,  359,290,  524,372]  # P7/128
+
+# P7-1280:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22,  54,36,  32,77,  70,83,  138,71,  75,173,  165,159,  148,334,  375,151,  334,317,  251,626,  499,474,  750,326,  534,814,  1079,818
+anchors_p7_1280:
+  - [19,22,  54,36,  32,77]  # P3/8
+  - [70,83,  138,71,  75,173]  # P4/16
+  - [165,159,  148,334,  375,151]  # P5/32
+  - [334,317,  251,626,  499,474]  # P6/64
+  - [750,326,  534,814,  1079,818]  # P7/128
+
+# P7-1920:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34,  81,55,  47,115,  105,124,  207,107,  113,259,  247,238,  222,500,  563,227,  501,476,  376,939,  749,711,  1126,489,  801,1222,  1618,1227
+anchors_p7_1920:
+  - [29,34,  81,55,  47,115]  # P3/8
+  - [105,124,  207,107,  113,259]  # P4/16
+  - [247,238,  222,500,  563,227]  # P5/32
+  - [501,476,  376,939,  749,711]  # P6/64
+  - [1126,489,  801,1222,  1618,1227]  # P7/128

yolov5processor/models/hub/yolov3-spp.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov3-tiny.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,14, 23,27, 37,58]  # P4/16
+  - [81,82, 135,169, 344,319]  # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [16, 3, 1]],  # 0
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
+   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
+  ]
+
+# YOLOv3-tiny head
+head:
+  [[-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
+
+   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
+  ]

yolov5processor/models/hub/yolov3.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5-bifpn.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]]
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 BiFPN head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14, 6], 1, Concat, [1]],  # cat P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5-fpn.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 6, BottleneckCSP, [1024]],  # 9
+  ]
+
+# YOLOv5 FPN head
+head:
+  [[-1, 3, BottleneckCSP, [1024, False]],  # 10 (P5/32-large)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 3, BottleneckCSP, [512, False]],  # 14 (P4/16-medium)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 3, BottleneckCSP, [256, False]],  # 18 (P3/8-small)
+
+   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5-p2.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 2], 1, Concat, [1]],  # cat backbone P2
+   [-1, 1, C3, [128, False]],  # 21 (P2/4-xsmall)
+
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P3
+   [-1, 3, C3, [256, False]],  # 24 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 27 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 30 (P5/32-large)
+
+   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5-p6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 1, SPP, [1024, [3, 5, 7]]],
+   [-1, 3, C3, [1024, False]],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P5/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/hub/yolov5-p7.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, Conv, [1280, 3, 2]],  # 11-P7/128
+   [-1, 1, SPP, [1280, [3, 5]]],
+   [-1, 3, C3, [1280, False]],  # 13
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [1024, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 10], 1, Concat, [1]],  # cat backbone P6
+   [-1, 3, C3, [1024, False]],  # 17
+
+   [-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 21
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 25
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 29 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 26], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 32 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 35 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 38 (P6/64-xlarge)
+
+   [-1, 1, Conv, [1024, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P7
+   [-1, 3, C3, [1280, False]],  # 41 (P7/128-xxlarge)
+
+   [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6, P7)
+  ]

yolov5processor/models/hub/yolov5-panet.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 PANet head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5l6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/hub/yolov5m6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/hub/yolov5n6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/hub/yolov5s-ghost.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, GhostConv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3Ghost, [128]],
+   [-1, 1, GhostConv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3Ghost, [256]],
+   [-1, 1, GhostConv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3Ghost, [512]],
+   [-1, 1, GhostConv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3Ghost, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, GhostConv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3Ghost, [512, False]],  # 13
+
+   [-1, 1, GhostConv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3Ghost, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, GhostConv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3Ghost, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, GhostConv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3Ghost, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5s-transformer.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3TR, [1024, False]],  # 9  <-------- C3TR() Transformer module
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/hub/yolov5s6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/hub/yolov5x6.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5processor/models/tf.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+TensorFlow, Keras and TFLite versions of YOLOv5
+Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
+
+Usage:
+    $ python models/tf.py --weights yolov5s.pt
+
+Export:
+    $ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
+"""
+
+import argparse
+import logging
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+import numpy as np
+import tensorflow as tf
+import torch
+import torch.nn as nn
+from tensorflow import keras
+
+from yolov5processor.models.common import Bottleneck, BottleneckCSP, Concat, Conv, C3, DWConv, Focus, SPP, SPPF, autopad
+from yolov5processor.models.experimental import CrossConv, MixConv2d, attempt_load
+from yolov5processor.models.yolo import Detect
+from yolov5processor.utils.general import make_divisible, print_args, set_logging
+from yolov5processor.utils.activations import SiLU
+
+LOGGER = logging.getLogger(__name__)
+
+
+class TFBN(keras.layers.Layer):
+    # TensorFlow BatchNormalization wrapper
+    def __init__(self, w=None):
+        super(TFBN, self).__init__()
+        self.bn = keras.layers.BatchNormalization(
+            beta_initializer=keras.initializers.Constant(w.bias.numpy()),
+            gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
+            moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
+            moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
+            epsilon=w.eps)
+
+    def call(self, inputs):
+        return self.bn(inputs)
+
+
+class TFPad(keras.layers.Layer):
+    def __init__(self, pad):
+        super(TFPad, self).__init__()
+        self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
+
+    def call(self, inputs):
+        return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
+
+
+class TFConv(keras.layers.Layer):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, weights, kernel, stride, padding, groups
+        super(TFConv, self).__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
+        # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
+        # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
+
+        conv = keras.layers.Conv2D(
+            c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
+            kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
+        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
+        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
+
+        # YOLOv5 activations
+        if isinstance(w.act, nn.LeakyReLU):
+            self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
+        elif isinstance(w.act, nn.Hardswish):
+            self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
+        elif isinstance(w.act, (nn.SiLU, SiLU)):
+            self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
+        else:
+            raise Exception(f'no matching TensorFlow activation found for {w.act}')
+
+    def call(self, inputs):
+        return self.act(self.bn(self.conv(inputs)))
+
+
+class TFFocus(keras.layers.Layer):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, kernel, stride, padding, groups
+        super(TFFocus, self).__init__()
+        self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
+
+    def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
+        # inputs = inputs / 255.  # normalize 0-255 to 0-1
+        return self.conv(tf.concat([inputs[:, ::2, ::2, :],
+                                    inputs[:, 1::2, ::2, :],
+                                    inputs[:, ::2, 1::2, :],
+                                    inputs[:, 1::2, 1::2, :]], 3))
+
+
+class TFBottleneck(keras.layers.Layer):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
+        super(TFBottleneck, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
+        self.add = shortcut and c1 == c2
+
+    def call(self, inputs):
+        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
+
+
+class TFConv2d(keras.layers.Layer):
+    # Substitution for PyTorch nn.Conv2D
+    def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
+        super(TFConv2d, self).__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        self.conv = keras.layers.Conv2D(
+            c2, k, s, 'VALID', use_bias=bias,
+            kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
+
+    def call(self, inputs):
+        return self.conv(inputs)
+
+
+class TFBottleneckCSP(keras.layers.Layer):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super(TFBottleneckCSP, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
+        self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
+        self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
+        self.bn = TFBN(w.bn)
+        self.act = lambda x: keras.activations.relu(x, alpha=0.1)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        y1 = self.cv3(self.m(self.cv1(inputs)))
+        y2 = self.cv2(inputs)
+        return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
+
+
+class TFC3(keras.layers.Layer):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super(TFC3, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
+        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
+
+
+class TFSPP(keras.layers.Layer):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13), w=None):
+        super(TFSPP, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
+        self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
+
+
+class TFSPPF(keras.layers.Layer):
+    # Spatial pyramid pooling-Fast layer
+    def __init__(self, c1, c2, k=5, w=None):
+        super(TFSPPF, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
+        self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        y1 = self.m(x)
+        y2 = self.m(y1)
+        return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
+
+
+class TFDetect(keras.layers.Layer):
+    def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
+        super(TFDetect, self).__init__()
+        self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [tf.zeros(1)] * self.nl  # init grid
+        self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
+        self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
+                                      [self.nl, 1, -1, 1, 2])
+        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
+        self.training = False  # set to False after building model
+        self.imgsz = imgsz
+        for i in range(self.nl):
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            self.grid[i] = self._make_grid(nx, ny)
+
+    def call(self, inputs):
+        z = []  # inference output
+        x = []
+        for i in range(self.nl):
+            x.append(self.m[i](inputs[i]))
+            # x(bs,20,20,255) to x(bs,3,20,20,85)
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
+
+            if not self.training:  # inference
+                y = tf.sigmoid(x[i])
+                xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
+                # Normalize xywh to 0-1 to reduce calibration error
+                xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                y = tf.concat([xy, wh, y[..., 4:]], -1)
+                z.append(tf.reshape(y, [-1, 3 * ny * nx, self.no]))
+
+        return x if self.training else (tf.concat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+        xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
+        return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
+
+
+class TFUpsample(keras.layers.Layer):
+    def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
+        super(TFUpsample, self).__init__()
+        assert scale_factor == 2, "scale_factor must be 2"
+        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
+        # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
+        # with default arguments: align_corners=False, half_pixel_centers=False
+        # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
+        #                                                            size=(x.shape[1] * 2, x.shape[2] * 2))
+
+    def call(self, inputs):
+        return self.upsample(inputs)
+
+
+class TFConcat(keras.layers.Layer):
+    def __init__(self, dimension=1, w=None):
+        super(TFConcat, self).__init__()
+        assert dimension == 1, "convert only NCHW to NHWC concat"
+        self.d = 3
+
+    def call(self, inputs):
+        return tf.concat(inputs, self.d)
+
+
+def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
+    LOGGER.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m_str = m
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except NameError:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
+            c1, c2 = ch[f], args[0]
+            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3]:
+                args.insert(2, n)
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
+        elif m is Detect:
+            args.append([ch[x + 1] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+            args.append(imgsz)
+        else:
+            c2 = ch[f]
+
+        tf_m = eval('TF' + m_str.replace('nn.', ''))
+        m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
+            else tf_m(*args, w=model.model[i])  # module
+
+        torch_m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum([x.numel() for x in torch_m_.parameters()])  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        ch.append(c2)
+    return keras.Sequential(layers), sorted(save)
+
+
+class TFModel:
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
+        super(TFModel, self).__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+
+        # Define model
+        if nc and nc != self.yaml['nc']:
+            print('Overriding %s nc=%g with nc=%g' % (cfg, self.yaml['nc'], nc))
+            self.yaml['nc'] = nc  # override yaml value
+        self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
+
+    def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
+                conf_thres=0.25):
+        y = []  # outputs
+        x = inputs
+        for i, m in enumerate(self.model.layers):
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            x = m(x)  # run
+            y.append(x if m.i in self.savelist else None)  # save output
+
+        # Add TensorFlow NMS
+        if tf_nms:
+            boxes = self._xywh2xyxy(x[0][..., :4])
+            probs = x[0][:, :, 4:5]
+            classes = x[0][:, :, 5:]
+            scores = probs * classes
+            if agnostic_nms:
+                nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
+                return nms, x[1]
+            else:
+                boxes = tf.expand_dims(boxes, 2)
+                nms = tf.image.combined_non_max_suppression(
+                    boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
+                return nms, x[1]
+
+        return x[0]  # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
+        # x = x[0][0]  # [x(1,6300,85), ...] to x(6300,85)
+        # xywh = x[..., :4]  # x(6300,4) boxes
+        # conf = x[..., 4:5]  # x(6300,1) confidences
+        # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1))  # x(6300,1)  classes
+        # return tf.concat([conf, cls, xywh], 1)
+
+    @staticmethod
+    def _xywh2xyxy(xywh):
+        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+        x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
+        return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
+
+
+class AgnosticNMS(keras.layers.Layer):
+    # TF Agnostic NMS
+    def call(self, input, topk_all, iou_thres, conf_thres):
+        # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
+        return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
+                         fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
+                         name='agnostic_nms')
+
+    @staticmethod
+    def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25):  # agnostic NMS
+        boxes, classes, scores = x
+        class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
+        scores_inp = tf.reduce_max(scores, -1)
+        selected_inds = tf.image.non_max_suppression(
+            boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
+        selected_boxes = tf.gather(boxes, selected_inds)
+        padded_boxes = tf.pad(selected_boxes,
+                              paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
+                              mode="CONSTANT", constant_values=0.0)
+        selected_scores = tf.gather(scores_inp, selected_inds)
+        padded_scores = tf.pad(selected_scores,
+                               paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                               mode="CONSTANT", constant_values=-1.0)
+        selected_classes = tf.gather(class_inds, selected_inds)
+        padded_classes = tf.pad(selected_classes,
+                                paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                                mode="CONSTANT", constant_values=-1.0)
+        valid_detections = tf.shape(selected_inds)[0]
+        return padded_boxes, padded_scores, padded_classes, valid_detections
+
+
+def representative_dataset_gen(dataset, ncalib=100):
+    # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
+    for n, (path, img, im0s, vid_cap) in enumerate(dataset):
+        input = np.transpose(img, [1, 2, 0])
+        input = np.expand_dims(input, axis=0).astype(np.float32)
+        input /= 255.0
+        yield [input]
+        if n >= ncalib:
+            break
+
+
+def run(weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=(640, 640),  # inference size h,w
+        batch_size=1,  # batch size
+        dynamic=False,  # dynamic batch size
+        ):
+    # PyTorch model
+    im = torch.zeros((batch_size, 3, *imgsz))  # BCHW image
+    model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
+    y = model(im)  # inference
+    model.info()
+
+    # TensorFlow model
+    im = tf.zeros((batch_size, *imgsz, 3))  # BHWC image
+    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+    y = tf_model.predict(im)  # inference
+
+    # Keras model
+    im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
+    keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
+    keras_model.summary()
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(FILE.stem, opt)
+    return opt
+
+
+def main(opt):
+    set_logging()
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

yolov5processor/models/yolo.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+YOLO-specific modules
+
+Usage:
+    $ python path/to/models/yolo.py --cfg yolov5s.yaml
+"""
+
+import argparse
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+from yolov5processor.models.common import *
+from yolov5processor.models.experimental import *
+from yolov5processor.utils.autoanchor import check_anchor_order
+from yolov5processor.utils.general import check_yaml, make_divisible, print_args, set_logging
+from yolov5processor.utils.plots import feature_visualization
+from yolov5processor.utils.torch_utils import copy_attr, fuse_conv_and_bn, initialize_weights, model_info, scale_img, \
+    select_device, time_sync
+
+try:
+    import thop  # for FLOPs computation
+except ImportError:
+    thop = None
+
+LOGGER = logging.getLogger(__name__)
+
+
+class Detect(nn.Module):
+    stride = None  # strides computed during build
+    onnx_dynamic = False  # ONNX export parameter
+
+    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
+        super().__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
+        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.inplace = inplace  # use in-place ops (e.g. slice assignment)
+
+    def forward(self, x):
+        z = []  # inference output
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
+                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
+
+                y = x[i].sigmoid()
+                if self.inplace:
+                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
+                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, y[..., 4:]), -1)
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    def _make_grid(self, nx=20, ny=20, i=0):
+        d = self.anchors[i].device
+        yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
+        grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
+        anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
+            .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
+        return grid, anchor_grid
+
+
+class Model(nn.Module):
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg, errors='ignore') as f:
+                self.yaml = yaml.safe_load(f)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        self.inplace = self.yaml.get('inplace', True)
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            s = 256  # 2x min stride
+            m.inplace = self.inplace
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            m.anchors /= m.stride.view(-1, 1, 1)
+            check_anchor_order(m)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        LOGGER.info('')
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        if augment:
+            return self._forward_augment(x)  # augmented inference, None
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_augment(self, x):
+        img_size = x.shape[-2:]  # height, width
+        s = [1, 0.83, 0.67]  # scales
+        f = [None, 3, None]  # flips (2-ud, 3-lr)
+        y = []  # outputs
+        for si, fi in zip(s, f):
+            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+            yi = self._forward_once(xi)[0]  # forward
+            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+            yi = self._descale_pred(yi, fi, si, img_size)
+            y.append(yi)
+        y = self._clip_augmented(y)  # clip augmented tails
+        return torch.cat(y, 1), None  # augmented inference, train
+
+    def _forward_once(self, x, profile=False, visualize=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+            if profile:
+                self._profile_one_layer(m, x, dt)
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+            if visualize:
+                feature_visualization(x, m.type, m.i, save_dir=visualize)
+        return x
+
+    def _descale_pred(self, p, flips, scale, img_size):
+        # de-scale predictions following augmented inference (inverse operation)
+        if self.inplace:
+            p[..., :4] /= scale  # de-scale
+            if flips == 2:
+                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
+            elif flips == 3:
+                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
+        else:
+            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
+            if flips == 2:
+                y = img_size[0] - y  # de-flip ud
+            elif flips == 3:
+                x = img_size[1] - x  # de-flip lr
+            p = torch.cat((x, y, wh, p[..., 4:]), -1)
+        return p
+
+    def _clip_augmented(self, y):
+        # Clip YOLOv5 augmented inference tails
+        nl = self.model[-1].nl  # number of detection layers (P3-P5)
+        g = sum(4 ** x for x in range(nl))  # grid points
+        e = 1  # exclude layer count
+        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
+        y[0] = y[0][:, :-i]  # large
+        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
+        y[-1] = y[-1][:, i:]  # small
+        return y
+
+    def _profile_one_layer(self, m, x, dt):
+        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
+        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
+        t = time_sync()
+        for _ in range(10):
+            m(x.copy() if c else x)
+        dt.append((time_sync() - t) * 100)
+        if m == self.model[0]:
+            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
+        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
+        if c:
+            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _print_biases(self):
+        m = self.model[-1]  # Detect() module
+        for mi in m.m:  # from
+            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
+            LOGGER.info(
+                ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+    # def _print_weights(self):
+    #     for m in self.model.modules():
+    #         if type(m) is Bottleneck:
+    #             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        LOGGER.info('Fusing layers... ')
+        for m in self.model.modules():
+            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.forward_fuse  # update forward
+        self.info()
+        return self
+
+    def autoshape(self):  # add AutoShape module
+        LOGGER.info('Adding AutoShape... ')
+        m = AutoShape(self)  # wrap model
+        copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributes
+        return m
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    LOGGER.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except NameError:
+                pass
+
+        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
+                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum([ch[x] for x in f])
+        elif m is Detect:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum([x.numel() for x in m_.parameters()])  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n_, np, t, args))  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--profile', action='store_true', help='profile model speed')
+    opt = parser.parse_args()
+    opt.cfg = check_yaml(opt.cfg)  # check YAML
+    print_args(FILE.stem, opt)
+    set_logging()
+    device = select_device(opt.device)
+
+    # Create model
+    model = Model(opt.cfg).to(device)
+    model.train()
+
+    # Profile
+    if opt.profile:
+        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+        y = model(img, profile=True)
+
+    # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
+    # from torch.utils.tensorboard import SummaryWriter
+    # tb_writer = SummaryWriter('.')
+    # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
+    # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), [])  # add model graph

yolov5processor/models/yolov5l.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/yolov5m.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/yolov5n.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/yolov5s.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/models/yolov5x.yaml

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5processor/utils/activations.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Activation functions
+"""
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
+class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
+    @staticmethod
+    def forward(x):
+        return x * torch.sigmoid(x)
+
+
+class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
+    @staticmethod
+    def forward(x):
+        # return x * F.hardsigmoid(x)  # for torchscript and CoreML
+        return x * F.hardtanh(x + 3, 0., 6.) / 6.  # for torchscript, CoreML and ONNX
+
+
+# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
+class Mish(nn.Module):
+    @staticmethod
+    def forward(x):
+        return x * F.softplus(x).tanh()
+
+
+class MemoryEfficientMish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            fx = F.softplus(x).tanh()
+            return grad_output * (fx + x * sx * (1 - fx * fx))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
+class FReLU(nn.Module):
+    def __init__(self, c1, k=3):  # ch_in, kernel
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
+        self.bn = nn.BatchNorm2d(c1)
+
+    def forward(self, x):
+        return torch.max(x, self.bn(self.conv(x)))
+
+
+# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
+class AconC(nn.Module):
+    r""" ACON activation (activate or not).
+    AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
+    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
+    """
+
+    def __init__(self, c1):
+        super().__init__()
+        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
+        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
+        self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
+
+    def forward(self, x):
+        dpx = (self.p1 - self.p2) * x
+        return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
+
+
+class MetaAconC(nn.Module):
+    r""" ACON activation (activate or not).
+    MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
+    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
+    """
+
+    def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
+        super().__init__()
+        c2 = max(r, c1 // r)
+        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
+        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
+        self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
+        self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
+        # self.bn1 = nn.BatchNorm2d(c2)
+        # self.bn2 = nn.BatchNorm2d(c1)
+
+    def forward(self, x):
+        y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
+        # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
+        # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y)))))  # bug/unstable
+        beta = torch.sigmoid(self.fc2(self.fc1(y)))  # bug patch BN layers removed
+        dpx = (self.p1 - self.p2) * x
+        return dpx * torch.sigmoid(beta * dpx) + self.p2 * x

yolov5processor/utils/augmentations.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Image augmentation functions
+"""
+
+import logging
+import math
+import random
+
+import cv2
+import numpy as np
+
+from yolov5processor.utils.general import colorstr, segment2box, resample_segments, check_version
+from yolov5processor.utils.metrics import bbox_ioa
+
+
+class Albumentations:
+    # YOLOv5 Albumentations class (optional, only used if package is installed)
+    def __init__(self):
+        self.transform = None
+        try:
+            import albumentations as A
+            check_version(A.__version__, '1.0.3')  # version requirement
+
+            self.transform = A.Compose([
+                A.Blur(p=0.01),
+                A.MedianBlur(p=0.01),
+                A.ToGray(p=0.01),
+                A.CLAHE(p=0.01),
+                A.RandomBrightnessContrast(p=0.0),
+                A.RandomGamma(p=0.0),
+                A.ImageCompression(quality_lower=75, p=0.0)],
+                bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
+
+            logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
+        except ImportError:  # package not installed, skip
+            pass
+        except Exception as e:
+            logging.info(colorstr('albumentations: ') + f'{e}')
+
+    def __call__(self, im, labels, p=1.0):
+        if self.transform and random.random() < p:
+            new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0])  # transformed
+            im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
+        return im, labels
+
+
+def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
+    # HSV color-space augmentation
+    if hgain or sgain or vgain:
+        r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
+        hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
+        dtype = im.dtype  # uint8
+
+        x = np.arange(0, 256, dtype=r.dtype)
+        lut_hue = ((x * r[0]) % 180).astype(dtype)
+        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
+        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+
+        im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
+        cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im)  # no return needed
+
+
+def hist_equalize(im, clahe=True, bgr=False):
+    # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255
+    yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
+    if clahe:
+        c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+        yuv[:, :, 0] = c.apply(yuv[:, :, 0])
+    else:
+        yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0])  # equalize Y channel histogram
+    return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB)  # convert YUV image to RGB
+
+
+def replicate(im, labels):
+    # Replicate labels
+    h, w = im.shape[:2]
+    boxes = labels[:, 1:].astype(int)
+    x1, y1, x2, y2 = boxes.T
+    s = ((x2 - x1) + (y2 - y1)) / 2  # side length (pixels)
+    for i in s.argsort()[:round(s.size * 0.5)]:  # smallest indices
+        x1b, y1b, x2b, y2b = boxes[i]
+        bh, bw = y2b - y1b, x2b - x1b
+        yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw))  # offset x, y
+        x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
+        im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b]  # im4[ymin:ymax, xmin:xmax]
+        labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
+
+    return im, labels
+
+
+def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
+    # Resize and pad image while meeting stride-multiple constraints
+    shape = im.shape[:2]  # current shape [height, width]
+    if isinstance(new_shape, int):
+        new_shape = (new_shape, new_shape)
+
+    # Scale ratio (new / old)
+    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
+    if not scaleup:  # only scale down, do not scale up (for better val mAP)
+        r = min(r, 1.0)
+
+    # Compute padding
+    ratio = r, r  # width, height ratios
+    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
+    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
+    if auto:  # minimum rectangle
+        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
+    elif scaleFill:  # stretch
+        dw, dh = 0.0, 0.0
+        new_unpad = (new_shape[1], new_shape[0])
+        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
+
+    dw /= 2  # divide padding into 2 sides
+    dh /= 2
+
+    if shape[::-1] != new_unpad:  # resize
+        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
+    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
+    return im, ratio, (dw, dh)
+
+
+def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
+                       border=(0, 0)):
+    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
+    # targets = [cls, xyxy]
+
+    height = im.shape[0] + border[0] * 2  # shape(h,w,c)
+    width = im.shape[1] + border[1] * 2
+
+    # Center
+    C = np.eye(3)
+    C[0, 2] = -im.shape[1] / 2  # x translation (pixels)
+    C[1, 2] = -im.shape[0] / 2  # y translation (pixels)
+
+    # Perspective
+    P = np.eye(3)
+    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
+    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)
+
+    # Rotation and Scale
+    R = np.eye(3)
+    a = random.uniform(-degrees, degrees)
+    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
+    s = random.uniform(1 - scale, 1 + scale)
+    # s = 2 ** random.uniform(-scale, scale)
+    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
+
+    # Shear
+    S = np.eye(3)
+    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
+    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)
+
+    # Translation
+    T = np.eye(3)
+    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
+    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)
+
+    # Combined rotation matrix
+    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
+    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
+        if perspective:
+            im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
+        else:  # affine
+            im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
+
+    # Visualize
+    # import matplotlib.pyplot as plt
+    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
+    # ax[0].imshow(im[:, :, ::-1])  # base
+    # ax[1].imshow(im2[:, :, ::-1])  # warped
+
+    # Transform label coordinates
+    n = len(targets)
+    if n:
+        use_segments = any(x.any() for x in segments)
+        new = np.zeros((n, 4))
+        if use_segments:  # warp segments
+            segments = resample_segments(segments)  # upsample
+            for i, segment in enumerate(segments):
+                xy = np.ones((len(segment), 3))
+                xy[:, :2] = segment
+                xy = xy @ M.T  # transform
+                xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]  # perspective rescale or affine
+
+                # clip
+                new[i] = segment2box(xy, width, height)
+
+        else:  # warp boxes
+            xy = np.ones((n * 4, 3))
+            xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
+            xy = xy @ M.T  # transform
+            xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine
+
+            # create new boxes
+            x = xy[:, [0, 2, 4, 6]]
+            y = xy[:, [1, 3, 5, 7]]
+            new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
+
+            # clip
+            new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
+            new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
+
+        # filter candidates
+        i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
+        targets = targets[i]
+        targets[:, 1:5] = new[i]
+
+    return im, targets
+
+
+def copy_paste(im, labels, segments, p=0.5):
+    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
+    n = len(segments)
+    if p and n:
+        h, w, c = im.shape  # height, width, channels
+        im_new = np.zeros(im.shape, np.uint8)
+        for j in random.sample(range(n), k=round(p * n)):
+            l, s = labels[j], segments[j]
+            box = w - l[3], l[2], w - l[1], l[4]
+            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
+            if (ioa < 0.30).all():  # allow 30% obscuration of existing labels
+                labels = np.concatenate((labels, [[l[0], *box]]), 0)
+                segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
+                cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
+
+        result = cv2.bitwise_and(src1=im, src2=im_new)
+        result = cv2.flip(result, 1)  # augment segments (flip left-right)
+        i = result > 0  # pixels to replace
+        # i[:, :] = result.max(2).reshape(h, w, 1)  # act over ch
+        im[i] = result[i]  # cv2.imwrite('debug.jpg', im)  # debug
+
+    return im, labels, segments
+
+
+def cutout(im, labels, p=0.5):
+    # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
+    if random.random() < p:
+        h, w = im.shape[:2]
+        scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16  # image size fraction
+        for s in scales:
+            mask_h = random.randint(1, int(h * s))  # create random masks
+            mask_w = random.randint(1, int(w * s))
+
+            # box
+            xmin = max(0, random.randint(0, w) - mask_w // 2)
+            ymin = max(0, random.randint(0, h) - mask_h // 2)
+            xmax = min(w, xmin + mask_w)
+            ymax = min(h, ymin + mask_h)
+
+            # apply random color mask
+            im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
+
+            # return unobscured labels
+            if len(labels) and s > 0.03:
+                box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
+                ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
+                labels = labels[ioa < 0.60]  # remove >60% obscured labels
+
+    return labels
+
+
+def mixup(im, labels, im2, labels2):
+    # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
+    r = np.random.beta(32.0, 32.0)  # mixup ratio, alpha=beta=32.0
+    im = (im * r + im2 * (1 - r)).astype(np.uint8)
+    labels = np.concatenate((labels, labels2), 0)
+    return im, labels
+
+
+def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16):  # box1(4,n), box2(4,n)
+    # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
+    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
+    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
+    ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
+    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates

yolov5processor/utils/autoanchor.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Auto-anchor utils
+"""
+
+import random
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from yolov5processor.utils.general import colorstr
+
+
+def check_anchor_order(m):
+    # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
+    a = m.anchors.prod(-1).view(-1)  # anchor area
+    da = a[-1] - a[0]  # delta a
+    ds = m.stride[-1] - m.stride[0]  # delta s
+    if da.sign() != ds.sign():  # same order
+        print('Reversing anchor order')
+        m.anchors[:] = m.anchors.flip(0)
+
+
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+    # Check anchor fit to data, recompute if necessary
+    prefix = colorstr('autoanchor: ')
+    print(f'\n{prefix}Analyzing anchors... ', end='')
+    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
+    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
+    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
+
+    def metric(k):  # compute metric
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        best = x.max(1)[0]  # best_x
+        aat = (x > 1. / thr).float().sum(1).mean()  # anchors above threshold
+        bpr = (best > 1. / thr).float().mean()  # best possible recall
+        return bpr, aat
+
+    anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1)  # current anchors
+    bpr, aat = metric(anchors.cpu().view(-1, 2))
+    print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
+    if bpr < 0.98:  # threshold to recompute
+        print('. Attempting to improve anchors, please wait...')
+        na = m.anchors.numel() // 2  # number of anchors
+        try:
+            anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+        except Exception as e:
+            print(f'{prefix}ERROR: {e}')
+        new_bpr = metric(anchors)[0]
+        if new_bpr > bpr:  # replace anchors
+            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
+            m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
+            check_anchor_order(m)
+            print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
+        else:
+            print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
+    print('')  # newline
+
+
+def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+    """ Creates kmeans-evolved anchors from training dataset
+
+        Arguments:
+            dataset: path to data.yaml, or a loaded dataset
+            n: number of anchors
+            img_size: image size used for training
+            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+            gen: generations to evolve anchors using genetic algorithm
+            verbose: print all results
+
+        Return:
+            k: kmeans evolved anchors
+
+        Usage:
+            from utils.autoanchor import *; _ = kmean_anchors()
+    """
+    from scipy.cluster.vq import kmeans
+
+    thr = 1. / thr
+    prefix = colorstr('autoanchor: ')
+
+    def metric(k, wh):  # compute metrics
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        # x = wh_iou(wh, torch.tensor(k))  # iou metric
+        return x, x.max(1)[0]  # x, best_x
+
+    def anchor_fitness(k):  # mutation fitness
+        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+        return (best * (best > thr).float()).mean()  # fitness
+
+    def print_results(k):
+        k = k[np.argsort(k.prod(1))]  # sort small to large
+        x, best = metric(k, wh0)
+        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
+        print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
+        print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
+              f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
+        for i, x in enumerate(k):
+            print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
+        return k
+
+    if isinstance(dataset, str):  # *.yaml file
+        with open(dataset, errors='ignore') as f:
+            data_dict = yaml.safe_load(f)  # model dict
+        from utils.datasets import LoadImagesAndLabels
+        dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
+
+    # Get label wh
+    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
+
+    # Filter
+    i = (wh0 < 3.0).any(1).sum()
+    if i:
+        print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
+    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
+    # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
+
+    # Kmeans calculation
+    print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
+    s = wh.std(0)  # sigmas for whitening
+    k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
+    assert len(k) == n, f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
+    k *= s
+    wh = torch.tensor(wh, dtype=torch.float32)  # filtered
+    wh0 = torch.tensor(wh0, dtype=torch.float32)  # unfiltered
+    k = print_results(k)
+
+    # Plot
+    # k, d = [None] * 20, [None] * 20
+    # for i in tqdm(range(1, 21)):
+    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+    # ax = ax.ravel()
+    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
+    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+    # fig.savefig('wh.png', dpi=200)
+
+    # Evolve
+    npr = np.random
+    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
+    pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:')  # progress bar
+    for _ in pbar:
+        v = np.ones(sh)
+        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
+            v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+        kg = (k.copy() * v).clip(min=2.0)
+        fg = anchor_fitness(kg)
+        if fg > f:
+            f, k = fg, kg.copy()
+            pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
+            if verbose:
+                print_results(k)
+
+    return print_results(k)

yolov5processor/utils/aws/mime.sh

+# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
+# This script will run on every instance restart, not only on first start
+# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
+
+Content-Type: multipart/mixed; boundary="//"
+MIME-Version: 1.0
+
+--//
+Content-Type: text/cloud-config; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="cloud-config.txt"
+
+#cloud-config
+cloud_final_modules:
+- [scripts-user, always]
+
+--//
+Content-Type: text/x-shellscript; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="userdata.txt"
+
+#!/bin/bash
+# --- paste contents of userdata.sh here ---
+--//

yolov5processor/utils/aws/resume.py

+# Resume all interrupted trainings in yolov5/ dir including DDP trainings
+# Usage: $ python utils/aws/resume.py
+
+import os
+import sys
+from pathlib import Path
+
+import torch
+import yaml
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[2]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+
+port = 0  # --master_port
+path = Path('').resolve()
+for last in path.rglob('*/**/last.pt'):
+    ckpt = torch.load(last)
+    if ckpt['optimizer'] is None:
+        continue
+
+    # Load opt.yaml
+    with open(last.parent.parent / 'opt.yaml', errors='ignore') as f:
+        opt = yaml.safe_load(f)
+
+    # Get device count
+    d = opt['device'].split(',')  # devices
+    nd = len(d)  # number of devices
+    ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1)  # distributed data parallel
+
+    if ddp:  # multi-GPU
+        port += 1
+        cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
+    else:  # single-GPU
+        cmd = f'python train.py --resume {last}'
+
+    cmd += ' > /dev/null 2>&1 &'  # redirect output to dev/null and run in daemon thread
+    print(cmd)
+    os.system(cmd)

yolov5processor/utils/aws/userdata.sh

+#!/bin/bash
+# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
+# This script will run only once on first instance start (for a re-start script see mime.sh)
+# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
+# Use >300 GB SSD
+
+cd home/ubuntu
+if [ ! -d yolov5 ]; then
+  echo "Running first-time script." # install dependencies, download COCO, pull Docker
+  git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
+  cd yolov5
+  bash data/scripts/get_coco.sh && echo "COCO done." &
+  sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
+  python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
+  wait && echo "All tasks done." # finish background tasks
+else
+  echo "Running re-start script." # resume interrupted runs
+  i=0
+  list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
+  while IFS= read -r id; do
+    ((i++))
+    echo "restarting container $i: $id"
+    sudo docker start $id
+    # sudo docker exec -it $id python train.py --resume # single-GPU
+    sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
+  done <<<"$list"
+fi

yolov5processor/utils/callbacks.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Callback utils
+"""
+
+
+class Callbacks:
+    """"
+    Handles all registered callbacks for YOLOv5 Hooks
+    """
+
+    # Define the available callbacks
+    _callbacks = {
+        'on_pretrain_routine_start': [],
+        'on_pretrain_routine_end': [],
+
+        'on_train_start': [],
+        'on_train_epoch_start': [],
+        'on_train_batch_start': [],
+        'optimizer_step': [],
+        'on_before_zero_grad': [],
+        'on_train_batch_end': [],
+        'on_train_epoch_end': [],
+
+        'on_val_start': [],
+        'on_val_batch_start': [],
+        'on_val_image_end': [],
+        'on_val_batch_end': [],
+        'on_val_end': [],
+
+        'on_fit_epoch_end': [],  # fit = train + val
+        'on_model_save': [],
+        'on_train_end': [],
+
+        'teardown': [],
+    }
+
+    def register_action(self, hook, name='', callback=None):
+        """
+        Register a new action to a callback hook
+
+        Args:
+            hook        The callback hook name to register the action to
+            name        The name of the action for later reference
+            callback    The callback to fire
+        """
+        assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
+        assert callable(callback), f"callback '{callback}' is not callable"
+        self._callbacks[hook].append({'name': name, 'callback': callback})
+
+    def get_registered_actions(self, hook=None):
+        """"
+        Returns all the registered actions by callback hook
+
+        Args:
+            hook The name of the hook to check, defaults to all
+        """
+        if hook:
+            return self._callbacks[hook]
+        else:
+            return self._callbacks
+
+    def run(self, hook, *args, **kwargs):
+        """
+        Loop through the registered actions and fire all callbacks
+
+        Args:
+            hook The name of the hook to check, defaults to all
+            args Arguments to receive from YOLOv5
+            kwargs Keyword Arguments to receive from YOLOv5
+        """
+
+        assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
+
+        for logger in self._callbacks[hook]:
+            logger['callback'](*args, **kwargs)

yolov5processor/utils/datasets.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Dataloaders and dataset utils
+"""
+
+import glob
+import hashlib
+import json
+import logging
+import os
+import random
+import shutil
+import time
+from itertools import repeat
+from multiprocessing.pool import ThreadPool, Pool
+from pathlib import Path
+from threading import Thread
+from zipfile import ZipFile
+
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+import yaml
+from PIL import Image, ExifTags
+from torch.utils.data import Dataset
+from tqdm import tqdm
+
+from yolov5processor.utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
+from yolov5processor.utils.general import check_dataset, check_requirements, check_yaml, clean_str, segments2boxes, \
+    xywh2xyxy, xywhn2xyxy, xyxy2xywhn, xyn2xy
+from yolov5processor.utils.torch_utils import torch_distributed_zero_first
+
+# Parameters
+HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
+IMG_FORMATS = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo']  # acceptable image suffixes
+VID_FORMATS = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes
+NUM_THREADS = min(8, os.cpu_count())  # number of multiprocessing threads
+
+# Get orientation exif tag
+for orientation in ExifTags.TAGS.keys():
+    if ExifTags.TAGS[orientation] == 'Orientation':
+        break
+
+
+def get_hash(paths):
+    # Returns a single hash value of a list of paths (files or dirs)
+    size = sum(os.path.getsize(p) for p in paths if os.path.exists(p))  # sizes
+    h = hashlib.md5(str(size).encode())  # hash sizes
+    h.update(''.join(paths).encode())  # hash paths
+    return h.hexdigest()  # return hash
+
+
+def exif_size(img):
+    # Returns exif-corrected PIL size
+    s = img.size  # (width, height)
+    try:
+        rotation = dict(img._getexif().items())[orientation]
+        if rotation == 6:  # rotation 270
+            s = (s[1], s[0])
+        elif rotation == 8:  # rotation 90
+            s = (s[1], s[0])
+    except:
+        pass
+
+    return s
+
+
+def exif_transpose(image):
+    """
+    Transpose a PIL image accordingly if it has an EXIF Orientation tag.
+    From https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py
+
+    :param image: The image to transpose.
+    :return: An image.
+    """
+    exif = image.getexif()
+    orientation = exif.get(0x0112, 1)  # default 1
+    if orientation > 1:
+        method = {2: Image.FLIP_LEFT_RIGHT,
+                  3: Image.ROTATE_180,
+                  4: Image.FLIP_TOP_BOTTOM,
+                  5: Image.TRANSPOSE,
+                  6: Image.ROTATE_270,
+                  7: Image.TRANSVERSE,
+                  8: Image.ROTATE_90,
+                  }.get(orientation)
+        if method is not None:
+            image = image.transpose(method)
+            del exif[0x0112]
+            image.info["exif"] = exif.tobytes()
+    return image
+
+
+def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
+                      rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix=''):
+    # Make sure only the first process in DDP process the dataset first, and the following others can use the cache
+    with torch_distributed_zero_first(rank):
+        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
+                                      augment=augment,  # augment images
+                                      hyp=hyp,  # augmentation hyperparameters
+                                      rect=rect,  # rectangular training
+                                      cache_images=cache,
+                                      single_cls=single_cls,
+                                      stride=int(stride),
+                                      pad=pad,
+                                      image_weights=image_weights,
+                                      prefix=prefix)
+
+    batch_size = min(batch_size, len(dataset))
+    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, workers])  # number of workers
+    sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
+    loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
+    # Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
+    dataloader = loader(dataset,
+                        batch_size=batch_size,
+                        num_workers=nw,
+                        sampler=sampler,
+                        pin_memory=True,
+                        collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
+    return dataloader, dataset
+
+
+class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
+    """ Dataloader that reuses workers
+
+    Uses same syntax as vanilla DataLoader
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
+        self.iterator = super().__iter__()
+
+    def __len__(self):
+        return len(self.batch_sampler.sampler)
+
+    def __iter__(self):
+        for i in range(len(self)):
+            yield next(self.iterator)
+
+
+class _RepeatSampler(object):
+    """ Sampler that repeats forever
+
+    Args:
+        sampler (Sampler)
+    """
+
+    def __init__(self, sampler):
+        self.sampler = sampler
+
+    def __iter__(self):
+        while True:
+            yield from iter(self.sampler)
+
+
+class LoadImages:
+    # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
+    def __init__(self, path, img_size=640, stride=32, auto=True):
+        p = str(Path(path).resolve())  # os-agnostic absolute path
+        if '*' in p:
+            files = sorted(glob.glob(p, recursive=True))  # glob
+        elif os.path.isdir(p):
+            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
+        elif os.path.isfile(p):
+            files = [p]  # files
+        else:
+            raise Exception(f'ERROR: {p} does not exist')
+
+        images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
+        videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
+        ni, nv = len(images), len(videos)
+
+        self.img_size = img_size
+        self.stride = stride
+        self.files = images + videos
+        self.nf = ni + nv  # number of files
+        self.video_flag = [False] * ni + [True] * nv
+        self.mode = 'image'
+        self.auto = auto
+        if any(videos):
+            self.new_video(videos[0])  # new video
+        else:
+            self.cap = None
+        assert self.nf > 0, f'No images or videos found in {p}. ' \
+                            f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'
+
+    def __iter__(self):
+        self.count = 0
+        return self
+
+    def __next__(self):
+        if self.count == self.nf:
+            raise StopIteration
+        path = self.files[self.count]
+
+        if self.video_flag[self.count]:
+            # Read video
+            self.mode = 'video'
+            ret_val, img0 = self.cap.read()
+            if not ret_val:
+                self.count += 1
+                self.cap.release()
+                if self.count == self.nf:  # last video
+                    raise StopIteration
+                else:
+                    path = self.files[self.count]
+                    self.new_video(path)
+                    ret_val, img0 = self.cap.read()
+
+            self.frame += 1
+            print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ', end='')
+
+        else:
+            # Read image
+            self.count += 1
+            img0 = cv2.imread(path)  # BGR
+            assert img0 is not None, 'Image Not Found ' + path
+            print(f'image {self.count}/{self.nf} {path}: ', end='')
+
+        # Padded resize
+        img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
+
+        # Convert
+        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
+        img = np.ascontiguousarray(img)
+
+        return path, img, img0, self.cap
+
+    def new_video(self, path):
+        self.frame = 0
+        self.cap = cv2.VideoCapture(path)
+        self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    def __len__(self):
+        return self.nf  # number of files
+
+
+class LoadWebcam:  # for inference
+    # YOLOv5 local webcam dataloader, i.e. `python detect.py --source 0`
+    def __init__(self, pipe='0', img_size=640, stride=32):
+        self.img_size = img_size
+        self.stride = stride
+        self.pipe = eval(pipe) if pipe.isnumeric() else pipe
+        self.cap = cv2.VideoCapture(self.pipe)  # video capture object
+        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            self.cap.release()
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Read frame
+        ret_val, img0 = self.cap.read()
+        img0 = cv2.flip(img0, 1)  # flip left-right
+
+        # Print
+        assert ret_val, f'Camera Error {self.pipe}'
+        img_path = 'webcam.jpg'
+        print(f'webcam {self.count}: ', end='')
+
+        # Padded resize
+        img = letterbox(img0, self.img_size, stride=self.stride)[0]
+
+        # Convert
+        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
+        img = np.ascontiguousarray(img)
+
+        return img_path, img, img0, None
+
+    def __len__(self):
+        return 0
+
+
+class LoadStreams:
+    # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
+    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
+        self.mode = 'stream'
+        self.img_size = img_size
+        self.stride = stride
+
+        if os.path.isfile(sources):
+            with open(sources, 'r') as f:
+                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
+        else:
+            sources = [sources]
+
+        n = len(sources)
+        self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
+        self.sources = [clean_str(x) for x in sources]  # clean source names for later
+        self.auto = auto
+        for i, s in enumerate(sources):  # index, source
+            # Start thread to read frames from video stream
+            print(f'{i + 1}/{n}: {s}... ', end='')
+            if 'youtube.com/' in s or 'youtu.be/' in s:  # if source is YouTube video
+                check_requirements(('pafy', 'youtube_dl'))
+                import pafy
+                s = pafy.new(s).getbest(preftype="mp4").url  # YouTube URL
+            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
+            cap = cv2.VideoCapture(s)
+            assert cap.isOpened(), f'Failed to open {s}'
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            self.fps[i] = max(cap.get(cv2.CAP_PROP_FPS) % 100, 0) or 30.0  # 30 FPS fallback
+            self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
+
+            _, self.imgs[i] = cap.read()  # guarantee first frame
+            self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
+            print(f" success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
+            self.threads[i].start()
+        print('')  # newline
+
+        # check for common shapes
+        s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
+        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
+        if not self.rect:
+            print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
+
+    def update(self, i, cap, stream):
+        # Read stream `i` frames in daemon thread
+        n, f, read = 0, self.frames[i], 1  # frame number, frame array, inference every 'read' frame
+        while cap.isOpened() and n < f:
+            n += 1
+            # _, self.imgs[index] = cap.read()
+            cap.grab()
+            if n % read == 0:
+                success, im = cap.retrieve()
+                if success:
+                    self.imgs[i] = im
+                else:
+                    print('WARNING: Video stream unresponsive, please check your IP camera connection.')
+                    self.imgs[i] *= 0
+                    cap.open(stream)  # re-open stream if signal was lost
+            time.sleep(1 / self.fps[i])  # wait time
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'):  # q to quit
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Letterbox
+        img0 = self.imgs.copy()
+        img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
+
+        # Stack
+        img = np.stack(img, 0)
+
+        # Convert
+        img = img[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW
+        img = np.ascontiguousarray(img)
+
+        return self.sources, img, img0, None
+
+    def __len__(self):
+        return len(self.sources)  # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+def img2label_paths(img_paths):
+    # Define label paths as a function of image paths
+    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
+    return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
+
+
+class LoadImagesAndLabels(Dataset):
+    # YOLOv5 train_loader/val_loader, loads images and labels for training and validation
+    cache_version = 0.5  # dataset labels *.cache version
+
+    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
+                 cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
+        self.img_size = img_size
+        self.augment = augment
+        self.hyp = hyp
+        self.image_weights = image_weights
+        self.rect = False if image_weights else rect
+        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
+        self.mosaic_border = [-img_size // 2, -img_size // 2]
+        self.stride = stride
+        self.path = path
+        self.albumentations = Albumentations() if augment else None
+
+        try:
+            f = []  # image files
+            for p in path if isinstance(path, list) else [path]:
+                p = Path(p)  # os-agnostic
+                if p.is_dir():  # dir
+                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
+                    # f = list(p.rglob('**/*.*'))  # pathlib
+                elif p.is_file():  # file
+                    with open(p, 'r') as t:
+                        t = t.read().strip().splitlines()
+                        parent = str(p.parent) + os.sep
+                        f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
+                        # f += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
+                else:
+                    raise Exception(f'{prefix}{p} does not exist')
+            self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS])
+            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats])  # pathlib
+            assert self.img_files, f'{prefix}No images found'
+        except Exception as e:
+            raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
+
+        # Check cache
+        self.label_files = img2label_paths(self.img_files)  # labels
+        cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
+        try:
+            cache, exists = np.load(cache_path, allow_pickle=True).item(), True  # load dict
+            assert cache['version'] == self.cache_version  # same version
+            assert cache['hash'] == get_hash(self.label_files + self.img_files)  # same hash
+        except:
+            cache, exists = self.cache_labels(cache_path, prefix), False  # cache
+
+        # Display cache
+        nf, nm, ne, nc, n = cache.pop('results')  # found, missing, empty, corrupted, total
+        if exists:
+            d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+            tqdm(None, desc=prefix + d, total=n, initial=n)  # display cache results
+            if cache['msgs']:
+                logging.info('\n'.join(cache['msgs']))  # display warnings
+        assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
+
+        # Read cache
+        [cache.pop(k) for k in ('hash', 'version', 'msgs')]  # remove items
+        labels, shapes, self.segments = zip(*cache.values())
+        self.labels = list(labels)
+        self.shapes = np.array(shapes, dtype=np.float64)
+        self.img_files = list(cache.keys())  # update
+        self.label_files = img2label_paths(cache.keys())  # update
+        n = len(shapes)  # number of images
+        bi = np.floor(np.arange(n) / batch_size).astype(np.int)  # batch index
+        nb = bi[-1] + 1  # number of batches
+        self.batch = bi  # batch index of image
+        self.n = n
+        self.indices = range(n)
+
+        # Update labels
+        include_class = []  # filter labels to include only these classes (optional)
+        include_class_array = np.array(include_class).reshape(1, -1)
+        for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
+            if include_class:
+                j = (label[:, 0:1] == include_class_array).any(1)
+                self.labels[i] = label[j]
+                if segment:
+                    self.segments[i] = segment[j]
+            if single_cls:  # single-class training, merge all classes into 0
+                self.labels[i][:, 0] = 0
+                if segment:
+                    self.segments[i][:, 0] = 0
+
+        # Rectangular Training
+        if self.rect:
+            # Sort by aspect ratio
+            s = self.shapes  # wh
+            ar = s[:, 1] / s[:, 0]  # aspect ratio
+            irect = ar.argsort()
+            self.img_files = [self.img_files[i] for i in irect]
+            self.label_files = [self.label_files[i] for i in irect]
+            self.labels = [self.labels[i] for i in irect]
+            self.shapes = s[irect]  # wh
+            ar = ar[irect]
+
+            # Set training image shapes
+            shapes = [[1, 1]] * nb
+            for i in range(nb):
+                ari = ar[bi == i]
+                mini, maxi = ari.min(), ari.max()
+                if maxi < 1:
+                    shapes[i] = [maxi, 1]
+                elif mini > 1:
+                    shapes[i] = [1, 1 / mini]
+
+            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
+
+        # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
+        self.imgs, self.img_npy = [None] * n, [None] * n
+        if cache_images:
+            if cache_images == 'disk':
+                self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy')
+                self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files]
+                self.im_cache_dir.mkdir(parents=True, exist_ok=True)
+            gb = 0  # Gigabytes of cached images
+            self.img_hw0, self.img_hw = [None] * n, [None] * n
+            results = ThreadPool(NUM_THREADS).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))
+            pbar = tqdm(enumerate(results), total=n)
+            for i, x in pbar:
+                if cache_images == 'disk':
+                    if not self.img_npy[i].exists():
+                        np.save(self.img_npy[i].as_posix(), x[0])
+                    gb += self.img_npy[i].stat().st_size
+                else:
+                    self.imgs[i], self.img_hw0[i], self.img_hw[i] = x  # im, hw_orig, hw_resized = load_image(self, i)
+                    gb += self.imgs[i].nbytes
+                pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
+            pbar.close()
+
+    def cache_labels(self, path=Path('./labels.cache'), prefix=''):
+        # Cache dataset labels, check images and read shapes
+        x = {}  # dict
+        nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
+        desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
+        with Pool(NUM_THREADS) as pool:
+            pbar = tqdm(pool.imap(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))),
+                        desc=desc, total=len(self.img_files))
+            for im_file, l, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
+                nm += nm_f
+                nf += nf_f
+                ne += ne_f
+                nc += nc_f
+                if im_file:
+                    x[im_file] = [l, shape, segments]
+                if msg:
+                    msgs.append(msg)
+                pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+
+        pbar.close()
+        if msgs:
+            logging.info('\n'.join(msgs))
+        if nf == 0:
+            logging.info(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
+        x['hash'] = get_hash(self.label_files + self.img_files)
+        x['results'] = nf, nm, ne, nc, len(self.img_files)
+        x['msgs'] = msgs  # warnings
+        x['version'] = self.cache_version  # cache version
+        try:
+            np.save(path, x)  # save cache for next time
+            path.with_suffix('.cache.npy').rename(path)  # remove .npy suffix
+            logging.info(f'{prefix}New cache created: {path}')
+        except Exception as e:
+            logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}')  # path not writeable
+        return x
+
+    def __len__(self):
+        return len(self.img_files)
+
+    # def __iter__(self):
+    #     self.count = -1
+    #     print('ran dataset iter')
+    #     #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
+    #     return self
+
+    def __getitem__(self, index):
+        index = self.indices[index]  # linear, shuffled, or image_weights
+
+        hyp = self.hyp
+        mosaic = self.mosaic and random.random() < hyp['mosaic']
+        if mosaic:
+            # Load mosaic
+            img, labels = load_mosaic(self, index)
+            shapes = None
+
+            # MixUp augmentation
+            if random.random() < hyp['mixup']:
+                img, labels = mixup(img, labels, *load_mosaic(self, random.randint(0, self.n - 1)))
+
+        else:
+            # Load image
+            img, (h0, w0), (h, w) = load_image(self, index)
+
+            # Letterbox
+            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
+            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling
+
+            labels = self.labels[index].copy()
+            if labels.size:  # normalized xywh to pixel xyxy format
+                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
+
+            if self.augment:
+                img, labels = random_perspective(img, labels,
+                                                 degrees=hyp['degrees'],
+                                                 translate=hyp['translate'],
+                                                 scale=hyp['scale'],
+                                                 shear=hyp['shear'],
+                                                 perspective=hyp['perspective'])
+
+        nl = len(labels)  # number of labels
+        if nl:
+            labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
+
+        if self.augment:
+            # Albumentations
+            img, labels = self.albumentations(img, labels)
+            nl = len(labels)  # update after albumentations
+
+            # HSV color-space
+            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+            # Flip up-down
+            if random.random() < hyp['flipud']:
+                img = np.flipud(img)
+                if nl:
+                    labels[:, 2] = 1 - labels[:, 2]
+
+            # Flip left-right
+            if random.random() < hyp['fliplr']:
+                img = np.fliplr(img)
+                if nl:
+                    labels[:, 1] = 1 - labels[:, 1]
+
+            # Cutouts
+            # labels = cutout(img, labels, p=0.5)
+
+        labels_out = torch.zeros((nl, 6))
+        if nl:
+            labels_out[:, 1:] = torch.from_numpy(labels)
+
+        # Convert
+        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
+        img = np.ascontiguousarray(img)
+
+        return torch.from_numpy(img), labels_out, self.img_files[index], shapes
+
+    @staticmethod
+    def collate_fn(batch):
+        img, label, path, shapes = zip(*batch)  # transposed
+        for i, l in enumerate(label):
+            l[:, 0] = i  # add target image index for build_targets()
+        return torch.stack(img, 0), torch.cat(label, 0), path, shapes
+
+    @staticmethod
+    def collate_fn4(batch):
+        img, label, path, shapes = zip(*batch)  # transposed
+        n = len(shapes) // 4
+        img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
+
+        ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
+        wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
+        s = torch.tensor([[1, 1, .5, .5, .5, .5]])  # scale
+        for i in range(n):  # zidane torch.zeros(16,3,720,1280)  # BCHW
+            i *= 4
+            if random.random() < 0.5:
+                im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
+                    0].type(img[i].type())
+                l = label[i]
+            else:
+                im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
+                l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
+            img4.append(im)
+            label4.append(l)
+
+        for i, l in enumerate(label4):
+            l[:, 0] = i  # add target image index for build_targets()
+
+        return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4
+
+
+# Ancillary functions --------------------------------------------------------------------------------------------------
+def load_image(self, i):
+    # loads 1 image from dataset index 'i', returns im, original hw, resized hw
+    im = self.imgs[i]
+    if im is None:  # not cached in ram
+        npy = self.img_npy[i]
+        if npy and npy.exists():  # load npy
+            im = np.load(npy)
+        else:  # read image
+            path = self.img_files[i]
+            im = cv2.imread(path)  # BGR
+            assert im is not None, 'Image Not Found ' + path
+        h0, w0 = im.shape[:2]  # orig hw
+        r = self.img_size / max(h0, w0)  # ratio
+        if r != 1:  # if sizes are not equal
+            im = cv2.resize(im, (int(w0 * r), int(h0 * r)),
+                            interpolation=cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR)
+        return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
+    else:
+        return self.imgs[i], self.img_hw0[i], self.img_hw[i]  # im, hw_original, hw_resized
+
+
+def load_mosaic(self, index):
+    # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
+    labels4, segments4 = [], []
+    s = self.img_size
+    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
+    indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
+    random.shuffle(indices)
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img4
+        if i == 0:  # top left
+            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
+        elif i == 1:  # top right
+            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+        elif i == 2:  # bottom left
+            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+        elif i == 3:  # bottom right
+            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        padw = x1a - x1b
+        padh = y1a - y1b
+
+        # Labels
+        labels, segments = self.labels[index].copy(), self.segments[index].copy()
+        if labels.size:
+            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
+            segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+        labels4.append(labels)
+        segments4.extend(segments)
+
+    # Concat/clip labels
+    labels4 = np.concatenate(labels4, 0)
+    for x in (labels4[:, 1:], *segments4):
+        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
+    # img4, labels4 = replicate(img4, labels4)  # replicate
+
+    # Augment
+    img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
+    img4, labels4 = random_perspective(img4, labels4, segments4,
+                                       degrees=self.hyp['degrees'],
+                                       translate=self.hyp['translate'],
+                                       scale=self.hyp['scale'],
+                                       shear=self.hyp['shear'],
+                                       perspective=self.hyp['perspective'],
+                                       border=self.mosaic_border)  # border to remove
+
+    return img4, labels4
+
+
+def load_mosaic9(self, index):
+    # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
+    labels9, segments9 = [], []
+    s = self.img_size
+    indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
+    random.shuffle(indices)
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img9
+        if i == 0:  # center
+            img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            h0, w0 = h, w
+            c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
+        elif i == 1:  # top
+            c = s, s - h, s + w, s
+        elif i == 2:  # top right
+            c = s + wp, s - h, s + wp + w, s
+        elif i == 3:  # right
+            c = s + w0, s, s + w0 + w, s + h
+        elif i == 4:  # bottom right
+            c = s + w0, s + hp, s + w0 + w, s + hp + h
+        elif i == 5:  # bottom
+            c = s + w0 - w, s + h0, s + w0, s + h0 + h
+        elif i == 6:  # bottom left
+            c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
+        elif i == 7:  # left
+            c = s - w, s + h0 - h, s, s + h0
+        elif i == 8:  # top left
+            c = s - w, s + h0 - hp - h, s, s + h0 - hp
+
+        padx, pady = c[:2]
+        x1, y1, x2, y2 = [max(x, 0) for x in c]  # allocate coords
+
+        # Labels
+        labels, segments = self.labels[index].copy(), self.segments[index].copy()
+        if labels.size:
+            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
+            segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
+        labels9.append(labels)
+        segments9.extend(segments)
+
+        # Image
+        img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
+        hp, wp = h, w  # height, width previous
+
+    # Offset
+    yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border]  # mosaic center x, y
+    img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
+
+    # Concat/clip labels
+    labels9 = np.concatenate(labels9, 0)
+    labels9[:, [1, 3]] -= xc
+    labels9[:, [2, 4]] -= yc
+    c = np.array([xc, yc])  # centers
+    segments9 = [x - c for x in segments9]
+
+    for x in (labels9[:, 1:], *segments9):
+        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
+    # img9, labels9 = replicate(img9, labels9)  # replicate
+
+    # Augment
+    img9, labels9 = random_perspective(img9, labels9, segments9,
+                                       degrees=self.hyp['degrees'],
+                                       translate=self.hyp['translate'],
+                                       scale=self.hyp['scale'],
+                                       shear=self.hyp['shear'],
+                                       perspective=self.hyp['perspective'],
+                                       border=self.mosaic_border)  # border to remove
+
+    return img9, labels9
+
+
+def create_folder(path='./new'):
+    # Create folder
+    if os.path.exists(path):
+        shutil.rmtree(path)  # delete output folder
+    os.makedirs(path)  # make new output folder
+
+
+def flatten_recursive(path='../datasets/coco128'):
+    # Flatten a recursive directory by bringing all files to top level
+    new_path = Path(path + '_flat')
+    create_folder(new_path)
+    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
+        shutil.copyfile(file, new_path / Path(file).name)
+
+
+def extract_boxes(path='../datasets/coco128'):  # from utils.datasets import *; extract_boxes()
+    # Convert detection dataset into classification dataset, with one directory per class
+    path = Path(path)  # images dir
+    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
+    files = list(path.rglob('*.*'))
+    n = len(files)  # number of files
+    for im_file in tqdm(files, total=n):
+        if im_file.suffix[1:] in IMG_FORMATS:
+            # image
+            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
+            h, w = im.shape[:2]
+
+            # labels
+            lb_file = Path(img2label_paths([str(im_file)])[0])
+            if Path(lb_file).exists():
+                with open(lb_file, 'r') as f:
+                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
+
+                for j, x in enumerate(lb):
+                    c = int(x[0])  # class
+                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
+                    if not f.parent.is_dir():
+                        f.parent.mkdir(parents=True)
+
+                    b = x[1:] * [w, h, w, h]  # box
+                    # b[2:] = b[2:].max()  # rectangle to square
+                    b[2:] = b[2:] * 1.2 + 3  # pad
+                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
+
+                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
+                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
+                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
+
+
+def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
+    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
+    Usage: from utils.datasets import *; autosplit()
+    Arguments
+        path:            Path to images directory
+        weights:         Train, val, test weights (list, tuple)
+        annotated_only:  Only use images with an annotated txt file
+    """
+    path = Path(path)  # images dir
+    files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in IMG_FORMATS], [])  # image files only
+    n = len(files)  # number of files
+    random.seed(0)  # for reproducibility
+    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+
+    txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
+    [(path.parent / x).unlink(missing_ok=True) for x in txt]  # remove existing
+
+    print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
+    for i, img in tqdm(zip(indices, files), total=n):
+        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
+            with open(path.parent / txt[i], 'a') as f:
+                f.write('./' + img.relative_to(path.parent).as_posix() + '\n')  # add image to txt file
+
+
+def verify_image_label(args):
+    # Verify one image-label pair
+    im_file, lb_file, prefix = args
+    nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', []  # number (missing, found, empty, corrupt), message, segments
+    try:
+        # verify images
+        im = Image.open(im_file)
+        im.verify()  # PIL verify
+        shape = exif_size(im)  # image size
+        assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
+        assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
+        if im.format.lower() in ('jpg', 'jpeg'):
+            with open(im_file, 'rb') as f:
+                f.seek(-2, 2)
+                if f.read() != b'\xff\xd9':  # corrupt JPEG
+                    Image.open(im_file).save(im_file, format='JPEG', subsampling=0, quality=100)  # re-save image
+                    msg = f'{prefix}WARNING: corrupt JPEG restored and saved {im_file}'
+
+        # verify labels
+        if os.path.isfile(lb_file):
+            nf = 1  # label found
+            with open(lb_file, 'r') as f:
+                l = [x.split() for x in f.read().strip().splitlines() if len(x)]
+                if any([len(x) > 8 for x in l]):  # is segment
+                    classes = np.array([x[0] for x in l], dtype=np.float32)
+                    segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l]  # (cls, xy1...)
+                    l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1)  # (cls, xywh)
+                l = np.array(l, dtype=np.float32)
+            if len(l):
+                assert l.shape[1] == 5, 'labels require 5 columns each'
+                assert (l >= 0).all(), 'negative labels'
+                assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
+                assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
+            else:
+                ne = 1  # label empty
+                l = np.zeros((0, 5), dtype=np.float32)
+        else:
+            nm = 1  # label missing
+            l = np.zeros((0, 5), dtype=np.float32)
+        return im_file, l, shape, segments, nm, nf, ne, nc, msg
+    except Exception as e:
+        nc = 1
+        msg = f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}'
+        return [None, None, None, None, nm, nf, ne, nc, msg]
+
+
+def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
+    """ Return dataset statistics dictionary with images and instances counts per split per class
+    To run in parent directory: export PYTHONPATH="$PWD/yolov5"
+    Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
+    Usage2: from utils.datasets import *; dataset_stats('../datasets/coco128_with_yaml.zip')
+    Arguments
+        path:           Path to data.yaml or data.zip (with data.yaml inside data.zip)
+        autodownload:   Attempt to download dataset if not found locally
+        verbose:        Print stats dictionary
+    """
+
+    def round_labels(labels):
+        # Update labels to integer class and 6 decimal place floats
+        return [[int(c), *[round(x, 4) for x in points]] for c, *points in labels]
+
+    def unzip(path):
+        # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
+        if str(path).endswith('.zip'):  # path is data.zip
+            assert Path(path).is_file(), f'Error unzipping {path}, file not found'
+            ZipFile(path).extractall(path=path.parent)  # unzip
+            dir = path.with_suffix('')  # dataset directory == zip name
+            return True, str(dir), next(dir.rglob('*.yaml'))  # zipped, data_dir, yaml_path
+        else:  # path is data.yaml
+            return False, None, path
+
+    def hub_ops(f, max_dim=1920):
+        # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
+        f_new = im_dir / Path(f).name  # dataset-hub image filename
+        try:  # use PIL
+            im = Image.open(f)
+            r = max_dim / max(im.height, im.width)  # ratio
+            if r < 1.0:  # image too large
+                im = im.resize((int(im.width * r), int(im.height * r)))
+            im.save(f_new, quality=75)  # save
+        except Exception as e:  # use OpenCV
+            print(f'WARNING: HUB ops PIL failure {f}: {e}')
+            im = cv2.imread(f)
+            im_height, im_width = im.shape[:2]
+            r = max_dim / max(im_height, im_width)  # ratio
+            if r < 1.0:  # image too large
+                im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_LINEAR)
+            cv2.imwrite(str(f_new), im)
+
+    zipped, data_dir, yaml_path = unzip(Path(path))
+    with open(check_yaml(yaml_path), errors='ignore') as f:
+        data = yaml.safe_load(f)  # data dict
+        if zipped:
+            data['path'] = data_dir  # TODO: should this be dir.resolve()?
+    check_dataset(data, autodownload)  # download dataset if missing
+    hub_dir = Path(data['path'] + ('-hub' if hub else ''))
+    stats = {'nc': data['nc'], 'names': data['names']}  # statistics dictionary
+    for split in 'train', 'val', 'test':
+        if data.get(split) is None:
+            stats[split] = None  # i.e. no test set
+            continue
+        x = []
+        dataset = LoadImagesAndLabels(data[split])  # load dataset
+        for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
+            x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc']))
+        x = np.array(x)  # shape(128x80)
+        stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
+                        'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
+                                        'per_class': (x > 0).sum(0).tolist()},
+                        'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
+                                   zip(dataset.img_files, dataset.labels)]}
+
+        if hub:
+            im_dir = hub_dir / 'images'
+            im_dir.mkdir(parents=True, exist_ok=True)
+            for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.img_files), total=dataset.n, desc='HUB Ops'):
+                pass
+
+    # Profile
+    stats_path = hub_dir / 'stats.json'
+    if profile:
+        for _ in range(1):
+            file = stats_path.with_suffix('.npy')
+            t1 = time.time()
+            np.save(file, stats)
+            t2 = time.time()
+            x = np.load(file, allow_pickle=True)
+            print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
+
+            file = stats_path.with_suffix('.json')
+            t1 = time.time()
+            with open(file, 'w') as f:
+                json.dump(stats, f)  # save stats *.json
+            t2 = time.time()
+            with open(file, 'r') as f:
+                x = json.load(f)  # load hyps dict
+            print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
+
+    # Save, print and return
+    if hub:
+        print(f'Saving {stats_path.resolve()}...')
+        with open(stats_path, 'w') as f:
+            json.dump(stats, f)  # save stats.json
+    if verbose:
+        print(json.dumps(stats, indent=2, sort_keys=False))
+    return stats

yolov5processor/utils/downloads.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Download utils
+"""
+
+import os
+import platform
+import subprocess
+import time
+import urllib
+from pathlib import Path
+from zipfile import ZipFile
+
+import requests
+import torch
+
+
+def gsutil_getsize(url=''):
+    # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
+    s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
+    return eval(s.split(' ')[0]) if len(s) else 0  # bytes
+
+
+def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
+    # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
+    file = Path(file)
+    assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
+    try:  # url1
+        print(f'Downloading {url} to {file}...')
+        torch.hub.download_url_to_file(url, str(file))
+        assert file.exists() and file.stat().st_size > min_bytes, assert_msg  # check
+    except Exception as e:  # url2
+        file.unlink(missing_ok=True)  # remove partial downloads
+        print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
+        os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -")  # curl download, retry and resume on fail
+    finally:
+        if not file.exists() or file.stat().st_size < min_bytes:  # check
+            file.unlink(missing_ok=True)  # remove partial downloads
+            print(f"ERROR: {assert_msg}\n{error_msg}")
+        print('')
+
+
+def attempt_download(file, repo='ultralytics/yolov5'):  # from utils.downloads import *; attempt_download()
+    # Attempt file download if does not exist
+    file = Path(str(file).strip().replace("'", ''))
+
+    if not file.exists():
+        # URL specified
+        name = Path(urllib.parse.unquote(str(file))).name  # decode '%2F' to '/' etc.
+        if str(file).startswith(('http:/', 'https:/')):  # download
+            url = str(file).replace(':/', '://')  # Pathlib turns :// -> :/
+            name = name.split('?')[0]  # parse authentication https://url.com/file.txt?auth...
+            safe_download(file=name, url=url, min_bytes=1E5)
+            return name
+
+        # GitHub assets
+        file.parent.mkdir(parents=True, exist_ok=True)  # make parent dir (if required)
+        try:
+            response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json()  # github api
+            assets = [x['name'] for x in response['assets']]  # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
+            tag = response['tag_name']  # i.e. 'v1.0'
+        except:  # fallback plan
+            assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
+                      'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
+            try:
+                tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
+            except:
+                tag = 'v6.0'  # current release
+
+        if name in assets:
+            safe_download(file,
+                          url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
+                          # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}',  # backup url (optional)
+                          min_bytes=1E5,
+                          error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/')
+
+    return str(file)
+
+
+def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
+    # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download()
+    t = time.time()
+    file = Path(file)
+    cookie = Path('cookie')  # gdrive cookie
+    print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
+    file.unlink(missing_ok=True)  # remove existing file
+    cookie.unlink(missing_ok=True)  # remove existing cookie
+
+    # Attempt file download
+    out = "NUL" if platform.system() == "Windows" else "/dev/null"
+    os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
+    if os.path.exists('cookie'):  # large file
+        s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
+    else:  # small file
+        s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
+    r = os.system(s)  # execute, capture return
+    cookie.unlink(missing_ok=True)  # remove existing cookie
+
+    # Error check
+    if r != 0:
+        file.unlink(missing_ok=True)  # remove partial
+        print('Download error ')  # raise Exception('Download error')
+        return r
+
+    # Unzip if archive
+    if file.suffix == '.zip':
+        print('unzipping... ', end='')
+        ZipFile(file).extractall(path=file.parent)  # unzip
+        file.unlink()  # remove zip
+
+    print(f'Done ({time.time() - t:.1f}s)')
+    return r
+
+
+def get_token(cookie="./cookie"):
+    with open(cookie) as f:
+        for line in f:
+            if "download" in line:
+                return line.split()[-1]
+    return ""
+
+# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
+#
+#
+# def upload_blob(bucket_name, source_file_name, destination_blob_name):
+#     # Uploads a file to a bucket
+#     # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
+#
+#     storage_client = storage.Client()
+#     bucket = storage_client.get_bucket(bucket_name)
+#     blob = bucket.blob(destination_blob_name)
+#
+#     blob.upload_from_filename(source_file_name)
+#
+#     print('File {} uploaded to {}.'.format(
+#         source_file_name,
+#         destination_blob_name))
+#
+#
+# def download_blob(bucket_name, source_blob_name, destination_file_name):
+#     # Uploads a blob from a bucket
+#     storage_client = storage.Client()
+#     bucket = storage_client.get_bucket(bucket_name)
+#     blob = bucket.blob(source_blob_name)
+#
+#     blob.download_to_filename(destination_file_name)
+#
+#     print('Blob {} downloaded to {}.'.format(
+#         source_blob_name,
+#         destination_file_name))

yolov5processor/utils/flask_rest_api/README.md

+# Flask REST API
+
+[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are
+commonly used to expose Machine Learning (ML)  models to other services. This folder contains an example REST API
+created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
+
+## Requirements
+
+[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
+
+```shell
+$ pip install Flask
+```
+
+## Run
+
+After Flask installation run:
+
+```shell
+$ python3 restapi.py --port 5000
+```
+
+Then use [curl](https://curl.se/) to perform a request:
+
+```shell
+$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'
+```
+
+The model inference results are returned as a JSON response:
+
+```json
+[
+  {
+    "class": 0,
+    "confidence": 0.8900438547,
+    "height": 0.9318675399,
+    "name": "person",
+    "width": 0.3264600933,
+    "xcenter": 0.7438579798,
+    "ycenter": 0.5207948685
+  },
+  {
+    "class": 0,
+    "confidence": 0.8440024257,
+    "height": 0.7155083418,
+    "name": "person",
+    "width": 0.6546785235,
+    "xcenter": 0.427829951,
+    "ycenter": 0.6334488392
+  },
+  {
+    "class": 27,
+    "confidence": 0.3771208823,
+    "height": 0.3902671337,
+    "name": "tie",
+    "width": 0.0696444362,
+    "xcenter": 0.3675483763,
+    "ycenter": 0.7991207838
+  },
+  {
+    "class": 27,
+    "confidence": 0.3527112305,
+    "height": 0.1540903747,
+    "name": "tie",
+    "width": 0.0336618312,
+    "xcenter": 0.7814827561,
+    "ycenter": 0.5065554976
+  }
+]
+```
+
+An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given
+in `example_request.py`

yolov5processor/utils/flask_rest_api/example_request.py

+"""Perform test request"""
+import pprint
+
+import requests
+
+DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s"
+TEST_IMAGE = "zidane.jpg"
+
+image_data = open(TEST_IMAGE, "rb").read()
+
+response = requests.post(DETECTION_URL, files={"image": image_data}).json()
+
+pprint.pprint(response)

yolov5processor/utils/flask_rest_api/restapi.py

+"""
+Run a rest API exposing the yolov5s object detection model
+"""
+import argparse
+import io
+
+import torch
+from PIL import Image
+from flask import Flask, request
+
+app = Flask(__name__)
+
+DETECTION_URL = "/v1/object-detection/yolov5s"
+
+
+@app.route(DETECTION_URL, methods=["POST"])
+def predict():
+    if not request.method == "POST":
+        return
+
+    if request.files.get("image"):
+        image_file = request.files["image"]
+        image_bytes = image_file.read()
+
+        img = Image.open(io.BytesIO(image_bytes))
+
+        results = model(img, size=640)  # reduce size=320 for faster inference
+        return results.pandas().xyxy[0].to_json(orient="records")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
+    parser.add_argument("--port", default=5000, type=int, help="port number")
+    args = parser.parse_args()
+
+    model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True)  # force_reload to recache
+    app.run(host="0.0.0.0", port=args.port)  # debug=True causes Restarting with stat

yolov5processor/utils/general.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+General utils
+"""
+
+import contextlib
+import glob
+import logging
+import math
+import os
+import platform
+import random
+import re
+import signal
+import time
+import urllib
+from itertools import repeat
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+from subprocess import check_output
+from zipfile import ZipFile
+
+import cv2
+import numpy as np
+import pandas as pd
+import pkg_resources as pkg
+import torch
+import torchvision
+import yaml
+
+from yolov5processor.utils.downloads import gsutil_getsize
+from yolov5processor.utils.metrics import box_iou, fitness
+
+# Settings
+torch.set_printoptions(linewidth=320, precision=5, profile='long')
+np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})  # format short g, %precision=5
+pd.options.display.max_columns = 10
+cv2.setNumThreads(0)  # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
+os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8))  # NumExpr max threads
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+
+
+class Profile(contextlib.ContextDecorator):
+    # Usage: @Profile() decorator or 'with Profile():' context manager
+    def __enter__(self):
+        self.start = time.time()
+
+    def __exit__(self, type, value, traceback):
+        print(f'Profile results: {time.time() - self.start:.5f}s')
+
+
+class Timeout(contextlib.ContextDecorator):
+    # Usage: @Timeout(seconds) decorator or 'with Timeout(seconds):' context manager
+    def __init__(self, seconds, *, timeout_msg='', suppress_timeout_errors=True):
+        self.seconds = int(seconds)
+        self.timeout_message = timeout_msg
+        self.suppress = bool(suppress_timeout_errors)
+
+    def _timeout_handler(self, signum, frame):
+        raise TimeoutError(self.timeout_message)
+
+    def __enter__(self):
+        signal.signal(signal.SIGALRM, self._timeout_handler)  # Set handler for SIGALRM
+        signal.alarm(self.seconds)  # start countdown for SIGALRM to be raised
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        signal.alarm(0)  # Cancel SIGALRM if it's scheduled
+        if self.suppress and exc_type is TimeoutError:  # Suppress TimeoutError
+            return True
+
+
+def try_except(func):
+    # try-except function. Usage: @try_except decorator
+    def handler(*args, **kwargs):
+        try:
+            func(*args, **kwargs)
+        except Exception as e:
+            print(e)
+
+    return handler
+
+
+def methods(instance):
+    # Get class/instance methods
+    return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")]
+
+
+def set_logging(rank=-1, verbose=True):
+    logging.basicConfig(
+        format="%(message)s",
+        level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
+
+
+def print_args(name, opt):
+    # Print argparser arguments
+    print(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
+
+
+def init_seeds(seed=0):
+    # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html
+    # cudnn seed 0 settings are slower and more reproducible, else faster and less reproducible
+    import torch.backends.cudnn as cudnn
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False)
+
+
+def get_latest_run(search_dir='.'):
+    # Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
+    last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
+    return max(last_list, key=os.path.getctime) if last_list else ''
+
+
+def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'):
+    # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required.
+    env = os.getenv(env_var)
+    if env:
+        path = Path(env)  # use environment variable
+    else:
+        cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'}  # 3 OS dirs
+        path = Path.home() / cfg.get(platform.system(), '')  # OS-specific config dir
+        path = (path if is_writeable(path) else Path('/tmp')) / dir  # GCP and AWS lambda fix, only /tmp is writeable
+    path.mkdir(exist_ok=True)  # make if required
+    return path
+
+
+def is_writeable(dir, test=False):
+    # Return True if directory has write permissions, test opening a file with write permissions if test=True
+    if test:  # method 1
+        file = Path(dir) / 'tmp.txt'
+        try:
+            with open(file, 'w'):  # open file with write permissions
+                pass
+            file.unlink()  # remove file
+            return True
+        except IOError:
+            return False
+    else:  # method 2
+        return os.access(dir, os.R_OK)  # possible issues on Windows
+
+
+def is_docker():
+    # Is environment a Docker container?
+    return Path('/workspace').exists()  # or Path('/.dockerenv').exists()
+
+
+def is_colab():
+    # Is environment a Google Colab instance?
+    try:
+        import google.colab
+        return True
+    except ImportError:
+        return False
+
+
+def is_pip():
+    # Is file in a pip package?
+    return 'site-packages' in Path(__file__).resolve().parts
+
+
+def is_ascii(s=''):
+    # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7)
+    s = str(s)  # convert list, tuple, None, etc. to str
+    return len(s.encode().decode('ascii', 'ignore')) == len(s)
+
+
+def is_chinese(s='人工智能'):
+    # Is string composed of any Chinese characters?
+    return re.search('[\u4e00-\u9fff]', s)
+
+
+def emojis(str=''):
+    # Return platform-dependent emoji-safe version of string
+    return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
+
+
+def file_size(path):
+    # Return file/dir size (MB)
+    path = Path(path)
+    if path.is_file():
+        return path.stat().st_size / 1E6
+    elif path.is_dir():
+        return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / 1E6
+    else:
+        return 0.0
+
+
+def check_online():
+    # Check internet connectivity
+    import socket
+    try:
+        socket.create_connection(("1.1.1.1", 443), 5)  # check host accessibility
+        return True
+    except OSError:
+        return False
+
+
+@try_except
+def check_git_status():
+    # Recommend 'git pull' if code is out of date
+    msg = ', for updates see https://github.com/ultralytics/yolov5'
+    print(colorstr('github: '), end='')
+    assert Path('.git').exists(), 'skipping check (not a git repository)' + msg
+    assert not is_docker(), 'skipping check (Docker image)' + msg
+    assert check_online(), 'skipping check (offline)' + msg
+
+    cmd = 'git fetch && git config --get remote.origin.url'
+    url = check_output(cmd, shell=True, timeout=5).decode().strip().rstrip('.git')  # git fetch
+    branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip()  # checked out
+    n = int(check_output(f'git rev-list {branch}..origin/master --count', shell=True))  # commits behind
+    if n > 0:
+        s = f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `git pull` or `git clone {url}` to update."
+    else:
+        s = f'up to date with {url} ✅'
+    print(emojis(s))  # emoji-safe
+
+
+def check_python(minimum='3.6.2'):
+    # Check current python version vs. required python version
+    check_version(platform.python_version(), minimum, name='Python ')
+
+
+def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False):
+    # Check version vs. required version
+    current, minimum = (pkg.parse_version(x) for x in (current, minimum))
+    result = (current == minimum) if pinned else (current >= minimum)
+    assert result, f'{name}{minimum} required by YOLOv5, but {name}{current} is currently installed'
+
+
+@try_except
+def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True):
+    # Check installed dependencies meet requirements (pass *.txt file or list of packages)
+    prefix = colorstr('red', 'bold', 'requirements:')
+    check_python()  # check python version
+    if isinstance(requirements, (str, Path)):  # requirements.txt file
+        file = Path(requirements)
+        assert file.exists(), f"{prefix} {file.resolve()} not found, check failed."
+        requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
+    else:  # list or tuple of packages
+        requirements = [x for x in requirements if x not in exclude]
+
+    n = 0  # number of packages updates
+    for r in requirements:
+        try:
+            pkg.require(r)
+        except Exception as e:  # DistributionNotFound or VersionConflict if requirements not met
+            s = f"{prefix} {r} not found and is required by YOLOv5"
+            if install:
+                print(f"{s}, attempting auto-update...")
+                try:
+                    assert check_online(), f"'pip install {r}' skipped (offline)"
+                    print(check_output(f"pip install '{r}'", shell=True).decode())
+                    n += 1
+                except Exception as e:
+                    print(f'{prefix} {e}')
+            else:
+                print(f'{s}. Please install and rerun your command.')
+
+    if n:  # if packages updated
+        source = file.resolve() if 'file' in locals() else requirements
+        s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
+            f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
+        print(emojis(s))
+
+
+def check_img_size(imgsz, s=32, floor=0):
+    # Verify image size is a multiple of stride s in each dimension
+    if isinstance(imgsz, int):  # integer i.e. img_size=640
+        new_size = max(make_divisible(imgsz, int(s)), floor)
+    else:  # list i.e. img_size=[640, 480]
+        new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz]
+    if new_size != imgsz:
+        print(f'WARNING: --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}')
+    return new_size
+
+
+def check_imshow():
+    # Check if environment supports image displays
+    try:
+        assert not is_docker(), 'cv2.imshow() is disabled in Docker environments'
+        assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments'
+        cv2.imshow('test', np.zeros((1, 1, 3)))
+        cv2.waitKey(1)
+        cv2.destroyAllWindows()
+        cv2.waitKey(1)
+        return True
+    except Exception as e:
+        print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
+        return False
+
+
+def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''):
+    # Check file(s) for acceptable suffixes
+    if file and suffix:
+        if isinstance(suffix, str):
+            suffix = [suffix]
+        for f in file if isinstance(file, (list, tuple)) else [file]:
+            assert Path(f).suffix.lower() in suffix, f"{msg}{f} acceptable suffix is {suffix}"
+
+
+def check_yaml(file, suffix=('.yaml', '.yml')):
+    # Search/download YAML file (if necessary) and return path, checking suffix
+    return check_file(file, suffix)
+
+
+def check_file(file, suffix=''):
+    # Search/download file (if necessary) and return path
+    check_suffix(file, suffix)  # optional
+    file = str(file)  # convert to str()
+    if Path(file).is_file() or file == '':  # exists
+        return file
+    elif file.startswith(('http:/', 'https:/')):  # download
+        url = str(Path(file)).replace(':/', '://')  # Pathlib turns :// -> :/
+        file = Path(urllib.parse.unquote(file).split('?')[0]).name  # '%2F' to '/', split https://url.com/file.txt?auth
+        print(f'Downloading {url} to {file}...')
+        torch.hub.download_url_to_file(url, file)
+        assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}'  # check
+        return file
+    else:  # search
+        files = []
+        for d in 'data', 'models', 'utils':  # search directories
+            files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True))  # find file
+        assert len(files), f'File not found: {file}'  # assert file was found
+        assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}"  # assert unique
+        return files[0]  # return file
+
+
+def check_dataset(data, autodownload=True):
+    # Download and/or unzip dataset if not found locally
+    # Usage: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128_with_yaml.zip
+
+    # Download (optional)
+    extract_dir = ''
+    if isinstance(data, (str, Path)) and str(data).endswith('.zip'):  # i.e. gs://bucket/dir/coco128.zip
+        download(data, dir='../datasets', unzip=True, delete=False, curl=False, threads=1)
+        data = next((Path('../datasets') / Path(data).stem).rglob('*.yaml'))
+        extract_dir, autodownload = data.parent, False
+
+    # Read yaml (optional)
+    if isinstance(data, (str, Path)):
+        with open(data, errors='ignore') as f:
+            data = yaml.safe_load(f)  # dictionary
+
+    # Parse yaml
+    path = extract_dir or Path(data.get('path') or '')  # optional 'path' default to '.'
+    for k in 'train', 'val', 'test':
+        if data.get(k):  # prepend path
+            data[k] = str(path / data[k]) if isinstance(data[k], str) else [str(path / x) for x in data[k]]
+
+    assert 'nc' in data, "Dataset 'nc' key missing."
+    if 'names' not in data:
+        data['names'] = [f'class{i}' for i in range(data['nc'])]  # assign class names if missing
+    train, val, test, s = [data.get(x) for x in ('train', 'val', 'test', 'download')]
+    if val:
+        val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
+        if not all(x.exists() for x in val):
+            print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
+            if s and autodownload:  # download script
+                root = path.parent if 'path' in data else '..'  # unzip directory i.e. '../'
+                if s.startswith('http') and s.endswith('.zip'):  # URL
+                    f = Path(s).name  # filename
+                    print(f'Downloading {s} to {f}...')
+                    torch.hub.download_url_to_file(s, f)
+                    Path(root).mkdir(parents=True, exist_ok=True)  # create root
+                    ZipFile(f).extractall(path=root)  # unzip
+                    Path(f).unlink()  # remove zip
+                    r = None  # success
+                elif s.startswith('bash '):  # bash script
+                    print(f'Running {s} ...')
+                    r = os.system(s)
+                else:  # python script
+                    r = exec(s, {'yaml': data})  # return None
+                print(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}\n")
+            else:
+                raise Exception('Dataset not found.')
+
+    return data  # dictionary
+
+
+def url2file(url):
+    # Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt
+    url = str(Path(url)).replace(':/', '://')  # Pathlib turns :// -> :/
+    file = Path(urllib.parse.unquote(url)).name.split('?')[0]  # '%2F' to '/', split https://url.com/file.txt?auth
+    return file
+
+
+def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
+    # Multi-threaded file download and unzip function, used in data.yaml for autodownload
+    def download_one(url, dir):
+        # Download 1 file
+        f = dir / Path(url).name  # filename
+        if Path(url).is_file():  # exists in current path
+            Path(url).rename(f)  # move to dir
+        elif not f.exists():
+            print(f'Downloading {url} to {f}...')
+            if curl:
+                os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -")  # curl download, retry and resume on fail
+            else:
+                torch.hub.download_url_to_file(url, f, progress=True)  # torch download
+        if unzip and f.suffix in ('.zip', '.gz'):
+            print(f'Unzipping {f}...')
+            if f.suffix == '.zip':
+                ZipFile(f).extractall(path=dir)  # unzip
+            elif f.suffix == '.gz':
+                os.system(f'tar xfz {f} --directory {f.parent}')  # unzip
+            if delete:
+                f.unlink()  # remove zip
+
+    dir = Path(dir)
+    dir.mkdir(parents=True, exist_ok=True)  # make directory
+    if threads > 1:
+        pool = ThreadPool(threads)
+        pool.imap(lambda x: download_one(*x), zip(url, repeat(dir)))  # multi-threaded
+        pool.close()
+        pool.join()
+    else:
+        for u in [url] if isinstance(url, (str, Path)) else url:
+            download_one(u, dir)
+
+
+def make_divisible(x, divisor):
+    # Returns x evenly divisible by divisor
+    return math.ceil(x / divisor) * divisor
+
+
+def clean_str(s):
+    # Cleans a string by replacing special characters with underscore _
+    return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
+
+
+def one_cycle(y1=0.0, y2=1.0, steps=100):
+    # lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf
+    return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
+
+
+def colorstr(*input):
+    # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')
+    *args, string = input if len(input) > 1 else ('blue', 'bold', input[0])  # color arguments, string
+    colors = {'black': '\033[30m',  # basic colors
+              'red': '\033[31m',
+              'green': '\033[32m',
+              'yellow': '\033[33m',
+              'blue': '\033[34m',
+              'magenta': '\033[35m',
+              'cyan': '\033[36m',
+              'white': '\033[37m',
+              'bright_black': '\033[90m',  # bright colors
+              'bright_red': '\033[91m',
+              'bright_green': '\033[92m',
+              'bright_yellow': '\033[93m',
+              'bright_blue': '\033[94m',
+              'bright_magenta': '\033[95m',
+              'bright_cyan': '\033[96m',
+              'bright_white': '\033[97m',
+              'end': '\033[0m',  # misc
+              'bold': '\033[1m',
+              'underline': '\033[4m'}
+    return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
+
+
+def labels_to_class_weights(labels, nc=80):
+    # Get class weights (inverse frequency) from training labels
+    if labels[0] is None:  # no labels loaded
+        return torch.Tensor()
+
+    labels = np.concatenate(labels, 0)  # labels.shape = (866643, 5) for COCO
+    classes = labels[:, 0].astype(np.int)  # labels = [class xywh]
+    weights = np.bincount(classes, minlength=nc)  # occurrences per class
+
+    # Prepend gridpoint count (for uCE training)
+    # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum()  # gridpoints per image
+    # weights = np.hstack([gpi * len(labels)  - weights.sum() * 9, weights * 9]) ** 0.5  # prepend gridpoints to start
+
+    weights[weights == 0] = 1  # replace empty bins with 1
+    weights = 1 / weights  # number of targets per class
+    weights /= weights.sum()  # normalize
+    return torch.from_numpy(weights)
+
+
+def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
+    # Produces image weights based on class_weights and image contents
+    class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
+    image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
+    # index = random.choices(range(n), weights=image_weights, k=1)  # weight image sample
+    return image_weights
+
+
+def coco80_to_coco91_class():  # converts 80-index (val2014) to 91-index (paper)
+    # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
+    # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
+    # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
+    # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
+    # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
+    x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
+         35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+         64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
+    return x
+
+
+def xyxy2xywh(x):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
+    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
+    y[:, 2] = x[:, 2] - x[:, 0]  # width
+    y[:, 3] = x[:, 3] - x[:, 1]  # height
+    return y
+
+
+def xywh2xyxy(x):
+    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
+    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
+    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
+    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
+    return y
+
+
+def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
+    # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw  # top left x
+    y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh  # top left y
+    y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw  # bottom right x
+    y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh  # bottom right y
+    return y
+
+
+def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right
+    if clip:
+        clip_coords(x, (h - eps, w - eps))  # warning: inplace clip
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w  # x center
+    y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h  # y center
+    y[:, 2] = (x[:, 2] - x[:, 0]) / w  # width
+    y[:, 3] = (x[:, 3] - x[:, 1]) / h  # height
+    return y
+
+
+def xyn2xy(x, w=640, h=640, padw=0, padh=0):
+    # Convert normalized segments into pixel segments, shape (n,2)
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = w * x[:, 0] + padw  # top left x
+    y[:, 1] = h * x[:, 1] + padh  # top left y
+    return y
+
+
+def segment2box(segment, width=640, height=640):
+    # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
+    x, y = segment.T  # segment xy
+    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
+    x, y, = x[inside], y[inside]
+    return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4))  # xyxy
+
+
+def segments2boxes(segments):
+    # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
+    boxes = []
+    for s in segments:
+        x, y = s.T  # segment xy
+        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
+    return xyxy2xywh(np.array(boxes))  # cls, xywh
+
+
+def resample_segments(segments, n=1000):
+    # Up-sample an (n,2) segment
+    for i, s in enumerate(segments):
+        x = np.linspace(0, len(s) - 1, n)
+        xp = np.arange(len(s))
+        segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T  # segment xy
+    return segments
+
+
+def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
+    # Rescale coords (xyxy) from img1_shape to img0_shape
+    if ratio_pad is None:  # calculate from img0_shape
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
+        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
+    else:
+        gain = ratio_pad[0][0]
+        pad = ratio_pad[1]
+
+    coords[:, [0, 2]] -= pad[0]  # x padding
+    coords[:, [1, 3]] -= pad[1]  # y padding
+    coords[:, :4] /= gain
+    clip_coords(coords, img0_shape)
+    return coords
+
+
+def clip_coords(boxes, shape):
+    # Clip bounding xyxy bounding boxes to image shape (height, width)
+    if isinstance(boxes, torch.Tensor):  # faster individually
+        boxes[:, 0].clamp_(0, shape[1])  # x1
+        boxes[:, 1].clamp_(0, shape[0])  # y1
+        boxes[:, 2].clamp_(0, shape[1])  # x2
+        boxes[:, 3].clamp_(0, shape[0])  # y2
+    else:  # np.array (faster grouped)
+        boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1])  # x1, x2
+        boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0])  # y1, y2
+
+
+def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
+                        labels=(), max_det=300):
+    """Runs Non-Maximum Suppression (NMS) on inference results
+
+    Returns:
+         list of detections, on (n,6) tensor per image [xyxy, conf, cls]
+    """
+
+    nc = prediction.shape[2] - 5  # number of classes
+    xc = prediction[..., 4] > conf_thres  # candidates
+
+    # Checks
+    assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
+    assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
+
+    # Settings
+    min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
+    max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
+    time_limit = 10.0  # seconds to quit after
+    redundant = True  # require redundant detections
+    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)
+    merge = False  # use merge-NMS
+
+    t = time.time()
+    output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
+    for xi, x in enumerate(prediction):  # image index, image inference
+        # Apply constraints
+        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
+        x = x[xc[xi]]  # confidence
+
+        # Cat apriori labels if autolabelling
+        if labels and len(labels[xi]):
+            l = labels[xi]
+            v = torch.zeros((len(l), nc + 5), device=x.device)
+            v[:, :4] = l[:, 1:5]  # box
+            v[:, 4] = 1.0  # conf
+            v[range(len(l)), l[:, 0].long() + 5] = 1.0  # cls
+            x = torch.cat((x, v), 0)
+
+        # If none remain process next image
+        if not x.shape[0]:
+            continue
+
+        # Compute conf
+        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf
+
+        # Box (center x, center y, width, height) to (x1, y1, x2, y2)
+        box = xywh2xyxy(x[:, :4])
+
+        # Detections matrix nx6 (xyxy, conf, cls)
+        if multi_label:
+            i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
+            x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
+        else:  # best class only
+            conf, j = x[:, 5:].max(1, keepdim=True)
+            x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
+
+        # Filter by class
+        if classes is not None:
+            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
+
+        # Apply finite constraint
+        # if not torch.isfinite(x).all():
+        #     x = x[torch.isfinite(x).all(1)]
+
+        # Check shape
+        n = x.shape[0]  # number of boxes
+        if not n:  # no boxes
+            continue
+        elif n > max_nms:  # excess boxes
+            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence
+
+        # Batched NMS
+        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
+        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
+        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
+        if i.shape[0] > max_det:  # limit detections
+            i = i[:max_det]
+        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
+            # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
+            iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
+            weights = iou * scores[None]  # box weights
+            x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
+            if redundant:
+                i = i[iou.sum(1) > 1]  # require redundancy
+
+        output[xi] = x[i]
+        if (time.time() - t) > time_limit:
+            print(f'WARNING: NMS time limit {time_limit}s exceeded')
+            break  # time limit exceeded
+
+    return output
+
+
+def strip_optimizer(f='best.pt', s=''):  # from utils.general import *; strip_optimizer()
+    # Strip optimizer from 'f' to finalize training, optionally save as 's'
+    x = torch.load(f, map_location=torch.device('cpu'))
+    if x.get('ema'):
+        x['model'] = x['ema']  # replace model with ema
+    for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates':  # keys
+        x[k] = None
+    x['epoch'] = -1
+    x['model'].half()  # to FP16
+    for p in x['model'].parameters():
+        p.requires_grad = False
+    torch.save(x, s or f)
+    mb = os.path.getsize(s or f) / 1E6  # filesize
+    print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
+
+
+def print_mutation(results, hyp, save_dir, bucket):
+    evolve_csv, results_csv, evolve_yaml = save_dir / 'evolve.csv', save_dir / 'results.csv', save_dir / 'hyp_evolve.yaml'
+    keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
+            'val/box_loss', 'val/obj_loss', 'val/cls_loss') + tuple(hyp.keys())  # [results + hyps]
+    keys = tuple(x.strip() for x in keys)
+    vals = results + tuple(hyp.values())
+    n = len(keys)
+
+    # Download (optional)
+    if bucket:
+        url = f'gs://{bucket}/evolve.csv'
+        if gsutil_getsize(url) > (os.path.getsize(evolve_csv) if os.path.exists(evolve_csv) else 0):
+            os.system(f'gsutil cp {url} {save_dir}')  # download evolve.csv if larger than local
+
+    # Log to evolve.csv
+    s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n')  # add header
+    with open(evolve_csv, 'a') as f:
+        f.write(s + ('%20.5g,' * n % vals).rstrip(',') + '\n')
+
+    # Print to screen
+    print(colorstr('evolve: ') + ', '.join(f'{x.strip():>20s}' for x in keys))
+    print(colorstr('evolve: ') + ', '.join(f'{x:20.5g}' for x in vals), end='\n\n\n')
+
+    # Save yaml
+    with open(evolve_yaml, 'w') as f:
+        data = pd.read_csv(evolve_csv)
+        data = data.rename(columns=lambda x: x.strip())  # strip keys
+        i = np.argmax(fitness(data.values[:, :7]))  #
+        f.write('# YOLOv5 Hyperparameter Evolution Results\n' +
+                f'# Best generation: {i}\n' +
+                f'# Last generation: {len(data)}\n' +
+                '# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + '\n' +
+                '# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n')
+        yaml.safe_dump(hyp, f, sort_keys=False)
+
+    if bucket:
+        os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}')  # upload
+
+
+def apply_classifier(x, model, img, im0):
+    # Apply a second stage classifier to yolo outputs
+    im0 = [im0] if isinstance(im0, np.ndarray) else im0
+    for i, d in enumerate(x):  # per image
+        if d is not None and len(d):
+            d = d.clone()
+
+            # Reshape and pad cutouts
+            b = xyxy2xywh(d[:, :4])  # boxes
+            b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # rectangle to square
+            b[:, 2:] = b[:, 2:] * 1.3 + 30  # pad
+            d[:, :4] = xywh2xyxy(b).long()
+
+            # Rescale boxes from img_size to im0 size
+            scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
+
+            # Classes
+            pred_cls1 = d[:, 5].long()
+            ims = []
+            for j, a in enumerate(d):  # per item
+                cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
+                im = cv2.resize(cutout, (224, 224))  # BGR
+                # cv2.imwrite('example%i.jpg' % j, cutout)
+
+                im = im[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+                im = np.ascontiguousarray(im, dtype=np.float32)  # uint8 to float32
+                im /= 255.0  # 0 - 255 to 0.0 - 1.0
+                ims.append(im)
+
+            pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1)  # classifier prediction
+            x[i] = x[i][pred_cls1 == pred_cls2]  # retain matching class detections
+
+    return x
+
+
+def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True):
+    # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
+    xyxy = torch.tensor(xyxy).view(-1, 4)
+    b = xyxy2xywh(xyxy)  # boxes
+    if square:
+        b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # attempt rectangle to square
+    b[:, 2:] = b[:, 2:] * gain + pad  # box wh * gain + pad
+    xyxy = xywh2xyxy(b).long()
+    clip_coords(xyxy, im.shape)
+    crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
+    if save:
+        cv2.imwrite(str(increment_path(file, mkdir=True).with_suffix('.jpg')), crop)
+    return crop
+
+
+def increment_path(path, exist_ok=False, sep='', mkdir=False):
+    # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
+    path = Path(path)  # os-agnostic
+    if path.exists() and not exist_ok:
+        suffix = path.suffix
+        path = path.with_suffix('')
+        dirs = glob.glob(f"{path}{sep}*")  # similar paths
+        matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
+        i = [int(m.groups()[0]) for m in matches if m]  # indices
+        n = max(i) + 1 if i else 2  # increment number
+        path = Path(f"{path}{sep}{n}{suffix}")  # update path
+    dir = path if path.suffix == '' else path.parent  # directory
+    if not dir.exists() and mkdir:
+        dir.mkdir(parents=True, exist_ok=True)  # make directory
+    return path

yolov5processor/utils/google_app_engine/Dockerfile

+FROM gcr.io/google-appengine/python
+
+# Create a virtualenv for dependencies. This isolates these packages from
+# system-level packages.
+# Use -p python3 or -p python3.7 to select python version. Default is version 2.
+RUN virtualenv /env -p python3
+
+# Setting these environment variables are the same as running
+# source /env/bin/activate.
+ENV VIRTUAL_ENV /env
+ENV PATH /env/bin:$PATH
+
+RUN apt-get update && apt-get install -y python-opencv
+
+# Copy the application's requirements.txt and run pip to install all
+# dependencies into the virtualenv.
+ADD requirements.txt /app/requirements.txt
+RUN pip install -r /app/requirements.txt
+
+# Add the application source code.
+ADD . /app
+
+# Run a WSGI server to serve the application. gunicorn must be declared as
+# a dependency in requirements.txt.
+CMD gunicorn -b :$PORT main:app

yolov5processor/utils/google_app_engine/additional_requirements.txt

+# add these requirements in your app on top of the existing ones
+pip==19.2
+Flask==1.0.2
+gunicorn==19.9.0

yolov5processor/utils/google_app_engine/app.yaml

+runtime: custom
+env: flex
+
+service: yolov5app
+
+liveness_check:
+  initial_delay_sec: 600
+
+manual_scaling:
+  instances: 1
+resources:
+  cpu: 1
+  memory_gb: 4
+  disk_size_gb: 20
\ No newline at end of file

yolov5processor/utils/loggers/__init__.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Logging utils
+"""
+
+import os
+import warnings
+from threading import Thread
+
+import pkg_resources as pkg
+import torch
+from torch.utils.tensorboard import SummaryWriter
+
+from utils.general import colorstr, emojis
+from utils.loggers.wandb.wandb_utils import WandbLogger
+from utils.plots import plot_images, plot_results
+from utils.torch_utils import de_parallel
+
+LOGGERS = ('csv', 'tb', 'wandb')  # text-file, TensorBoard, Weights & Biases
+RANK = int(os.getenv('RANK', -1))
+
+try:
+    import wandb
+
+    assert hasattr(wandb, '__version__')  # verify package import not local dir
+    if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]:
+        wandb_login_success = wandb.login(timeout=30)
+        if not wandb_login_success:
+            wandb = None
+except (ImportError, AssertionError):
+    wandb = None
+
+
+class Loggers():
+    # YOLOv5 Loggers class
+    def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS):
+        self.save_dir = save_dir
+        self.weights = weights
+        self.opt = opt
+        self.hyp = hyp
+        self.logger = logger  # for printing results to console
+        self.include = include
+        self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss',  # train loss
+                     'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',  # metrics
+                     'val/box_loss', 'val/obj_loss', 'val/cls_loss',  # val loss
+                     'x/lr0', 'x/lr1', 'x/lr2']  # params
+        for k in LOGGERS:
+            setattr(self, k, None)  # init empty logger dictionary
+        self.csv = True  # always log to csv
+
+        # Message
+        if not wandb:
+            prefix = colorstr('Weights & Biases: ')
+            s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)"
+            print(emojis(s))
+
+        # TensorBoard
+        s = self.save_dir
+        if 'tb' in self.include and not self.opt.evolve:
+            prefix = colorstr('TensorBoard: ')
+            self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/")
+            self.tb = SummaryWriter(str(s))
+
+        # W&B
+        if wandb and 'wandb' in self.include:
+            wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://')
+            run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None
+            self.opt.hyp = self.hyp  # add hyperparameters
+            self.wandb = WandbLogger(self.opt, run_id)
+        else:
+            self.wandb = None
+
+    def on_pretrain_routine_end(self):
+        # Callback runs on pre-train routine end
+        paths = self.save_dir.glob('*labels*.jpg')  # training labels
+        if self.wandb:
+            self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]})
+
+    def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn):
+        # Callback runs on train batch end
+        if plots:
+            if ni == 0:
+                if not sync_bn:  # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754
+                    with warnings.catch_warnings():
+                        warnings.simplefilter('ignore')  # suppress jit trace warning
+                        self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), [])
+            if ni < 3:
+                f = self.save_dir / f'train_batch{ni}.jpg'  # filename
+                Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
+            if self.wandb and ni == 10:
+                files = sorted(self.save_dir.glob('train*.jpg'))
+                self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]})
+
+    def on_train_epoch_end(self, epoch):
+        # Callback runs on train epoch end
+        if self.wandb:
+            self.wandb.current_epoch = epoch + 1
+
+    def on_val_image_end(self, pred, predn, path, names, im):
+        # Callback runs on val image end
+        if self.wandb:
+            self.wandb.val_one_image(pred, predn, path, names, im)
+
+    def on_val_end(self):
+        # Callback runs on val end
+        if self.wandb:
+            files = sorted(self.save_dir.glob('val*.jpg'))
+            self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]})
+
+    def on_fit_epoch_end(self, vals, epoch, best_fitness, fi):
+        # Callback runs at the end of each fit (train+val) epoch
+        x = {k: v for k, v in zip(self.keys, vals)}  # dict
+        if self.csv:
+            file = self.save_dir / 'results.csv'
+            n = len(x) + 1  # number of cols
+            s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n')  # add header
+            with open(file, 'a') as f:
+                f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n')
+
+        if self.tb:
+            for k, v in x.items():
+                self.tb.add_scalar(k, v, epoch)
+
+        if self.wandb:
+            self.wandb.log(x)
+            self.wandb.end_epoch(best_result=best_fitness == fi)
+
+    def on_model_save(self, last, epoch, final_epoch, best_fitness, fi):
+        # Callback runs on model save event
+        if self.wandb:
+            if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
+                self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi)
+
+    def on_train_end(self, last, best, plots, epoch):
+        # Callback runs on training end
+        if plots:
+            plot_results(file=self.save_dir / 'results.csv')  # save results.png
+        files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
+        files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()]  # filter
+
+        if self.tb:
+            import cv2
+            for f in files:
+                self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC')
+
+        if self.wandb:
+            self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]})
+            # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model
+            if not self.opt.evolve:
+                wandb.log_artifact(str(best if best.exists() else last), type='model',
+                                   name='run_' + self.wandb.wandb_run.id + '_model',
+                                   aliases=['latest', 'best', 'stripped'])
+                self.wandb.finish_run()
+            else:
+                self.wandb.finish_run()
+                self.wandb = WandbLogger(self.opt)

yolov5processor/utils/loggers/wandb/README.md

+📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 29 September 2021.
+* [About Weights & Biases](#about-weights-&-biases)
+* [First-Time Setup](#first-time-setup)
+* [Viewing runs](#viewing-runs)
+* [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage)
+* [Reports: Share your work with the world!](#reports)
+
+## About Weights & Biases
+Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions.
+
+Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows:
+
+ * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time
+ * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically
+ * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization
+ * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators
+ * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently
+ * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models
+
+## First-Time Setup
+<details open>
+ <summary> Toggle Details </summary>
+When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device.
+
+W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as:
+
+ ```shell
+ $ python train.py --project ... --name ...
+ ```
+
+YOLOv5 notebook example: <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
+<img width="960" alt="Screen Shot 2021-09-29 at 10 23 13 PM" src="https://user-images.githubusercontent.com/26833433/135392431-1ab7920a-c49d-450a-b0b0-0c86ec86100e.png">
+
+
+ </details>
+
+## Viewing Runs
+<details open>
+  <summary> Toggle Details </summary>
+Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in <b>realtime</b> . All important information is logged:
+
+ * Training & Validation losses
+ * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95
+ * Learning Rate over time
+ * A bounding box debugging panel, showing the training progress over time
+ * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage**
+ * System: Disk I/0, CPU utilization, RAM memory usage
+ * Your trained model as W&B Artifact
+ * Environment: OS and Python types, Git repository and state, **training command**
+
+<p align="center"><img width="900" alt="Weights & Biases dashboard" src="https://user-images.githubusercontent.com/26833433/135390767-c28b050f-8455-4004-adb0-3b730386e2b2.png"></p>
+
+
+</details>
+
+## Advanced Usage
+You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started.
+<details open>
+ <h3>1. Visualize and Version Datasets</h3>
+ Log, visualize, dynamically query, and understand your data with <a href='https://docs.wandb.ai/guides/data-vis/tables'>W&B Tables</a>. You can use the following command to log your dataset as a W&B Table. This will generate a <code>{dataset}_wandb.yaml</code> file which can be used to train from dataset artifact.
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. </code>
+   
+ ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png)
+ </details>
+  
+ <h3> 2: Train and Log Evaluation simultaneousy </h3>
+   This is an extension of the previous section, but it'll also training after uploading the dataset. <b> This also evaluation Table</b>
+   Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets,
+   so no images will be uploaded from your system more than once.
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --data ..  --upload_data </code>
+   
+![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png)
+ </details>
+  
+ <h3> 3: Train using dataset artifact </h3>
+   When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that 
+   can be used to train a model directly from the dataset artifact. <b> This also logs evaluation </b>
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --data {data}_wandb.yaml </code>
+   
+![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png)
+ </details>
+  
+   <h3> 4: Save model checkpoints as artifacts </h3>
+  To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. 
+  You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged
+
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python train.py --save_period 1 </code>
+   
+![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png)
+ </details>
+  
+</details>
+
+ <h3> 5: Resume runs from checkpoint artifacts. </h3>
+Any run can be resumed using artifacts if the <code>--resume</code> argument starts with <code>wandb-artifact://</code> prefix followed by the run path, i.e, <code>wandb-artifact://username/project/runid </code>. This doesn't require the model checkpoint to be present on the local system.
+
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python train.py --resume wandb-artifact://{run_path} </code>
+  
+![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png)
+ </details>
+ 
+  <h3> 6: Resume runs from dataset artifact & checkpoint artifacts. </h3>
+ <b> Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device </b>
+ The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot <code>--upload_dataset</code> or 
+ train from <code>_wandb.yaml</code> file and set <code>--save_period</code>
+
+ <details>
+  <summary> <b>Usage</b> </summary>
+   <b>Code</b> <code> $ python train.py --resume wandb-artifact://{run_path} </code>
+  
+![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png)
+ </details>
+  
+</details>
+
+
+ <h3> Reports </h3>
+W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)).
+ 
+<img width="900" alt="Weights & Biases Reports" src="https://user-images.githubusercontent.com/26833433/135394029-a17eaf86-c6c1-4b1d-bb80-b90e83aaffa7.png">
+
+
+## Environments
+
+YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):
+
+- **Google Colab and Kaggle** notebooks with free GPU: <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
+- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)
+- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)
+- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <a href="https://hub.docker.com/r/ultralytics/yolov5"><img src="https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker" alt="Docker Pulls"></a>
+
+
+## Status
+
+![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)
+
+If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

yolov5processor/utils/loggers/wandb/log_dataset.py

+import argparse
+
+from wandb_utils import WandbLogger
+
+WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
+
+
+def create_dataset_artifact(opt):
+    logger = WandbLogger(opt, None, job_type='Dataset Creation')  # TODO: return value unused
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
+    parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
+    parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project')
+    parser.add_argument('--entity', default=None, help='W&B entity')
+    parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run')
+
+    opt = parser.parse_args()
+    opt.resume = False  # Explicitly disallow resume check for dataset upload job
+
+    create_dataset_artifact(opt)

yolov5processor/utils/loggers/wandb/sweep.py

+import sys
+from pathlib import Path
+
+import wandb
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+
+from train import train, parse_opt
+from utils.general import increment_path
+from utils.torch_utils import select_device
+from utils.callbacks import Callbacks
+
+
+def sweep():
+    wandb.init()
+    # Get hyp dict from sweep agent
+    hyp_dict = vars(wandb.config).get("_items")
+
+    # Workaround: get necessary opt args
+    opt = parse_opt(known=True)
+    opt.batch_size = hyp_dict.get("batch_size")
+    opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve))
+    opt.epochs = hyp_dict.get("epochs")
+    opt.nosave = True
+    opt.data = hyp_dict.get("data")
+    device = select_device(opt.device, batch_size=opt.batch_size)
+
+    # train
+    train(hyp_dict, opt, device, callbacks=Callbacks())
+
+
+if __name__ == "__main__":
+    sweep()

yolov5processor/utils/loggers/wandb/sweep.yaml

+# Hyperparameters for training
+# To set range- 
+# Provide min and max values as:
+#      parameter:
+#         
+#         min: scalar
+#         max: scalar
+# OR
+#
+# Set a specific list of search space-
+#     parameter: 
+#         values: [scalar1, scalar2, scalar3...]
+#         
+# You can use grid, bayesian and hyperopt search strategy 
+# For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration
+
+program: utils/loggers/wandb/sweep.py
+method: random
+metric:
+  name: metrics/mAP_0.5
+  goal: maximize
+
+parameters:
+  # hyperparameters: set either min, max range or values list
+  data:
+    value: "data/coco128.yaml"
+  batch_size:
+    values: [64]
+  epochs:
+    values: [10]
+
+  lr0:
+    distribution: uniform
+    min: 1e-5
+    max: 1e-1
+  lrf:
+    distribution: uniform
+    min: 0.01
+    max: 1.0
+  momentum:
+    distribution: uniform
+    min: 0.6
+    max: 0.98
+  weight_decay:
+    distribution: uniform
+    min: 0.0
+    max: 0.001
+  warmup_epochs:
+    distribution: uniform
+    min: 0.0
+    max: 5.0
+  warmup_momentum:
+    distribution: uniform
+    min: 0.0
+    max: 0.95
+  warmup_bias_lr:
+    distribution: uniform
+    min: 0.0
+    max: 0.2
+  box:
+    distribution: uniform
+    min: 0.02
+    max: 0.2
+  cls:
+    distribution: uniform
+    min: 0.2
+    max: 4.0
+  cls_pw:
+    distribution: uniform
+    min: 0.5
+    max: 2.0
+  obj:
+    distribution: uniform
+    min: 0.2
+    max: 4.0
+  obj_pw:
+    distribution: uniform
+    min: 0.5
+    max: 2.0
+  iou_t:
+    distribution: uniform
+    min: 0.1
+    max: 0.7
+  anchor_t:
+    distribution: uniform
+    min: 2.0
+    max: 8.0
+  fl_gamma:
+    distribution: uniform
+    min: 0.0
+    max: 0.1
+  hsv_h:
+    distribution: uniform
+    min: 0.0
+    max: 0.1
+  hsv_s:
+    distribution: uniform
+    min: 0.0
+    max: 0.9
+  hsv_v:
+    distribution: uniform
+    min: 0.0
+    max: 0.9
+  degrees:
+    distribution: uniform
+    min: 0.0
+    max: 45.0
+  translate:
+    distribution: uniform
+    min: 0.0
+    max: 0.9
+  scale:
+    distribution: uniform
+    min: 0.0
+    max: 0.9
+  shear:
+    distribution: uniform
+    min: 0.0
+    max: 10.0
+  perspective:
+    distribution: uniform
+    min: 0.0
+    max: 0.001
+  flipud:
+    distribution: uniform
+    min: 0.0
+    max: 1.0
+  fliplr:
+    distribution: uniform
+    min: 0.0
+    max: 1.0
+  mosaic:
+    distribution: uniform
+    min: 0.0
+    max: 1.0
+  mixup:
+    distribution: uniform
+    min: 0.0
+    max: 1.0
+  copy_paste:
+    distribution: uniform
+    min: 0.0
+    max: 1.0

yolov5processor/utils/loggers/wandb/wandb_utils.py

+"""Utilities and tools for tracking runs with Weights & Biases."""
+
+import logging
+import os
+import sys
+from contextlib import contextmanager
+from pathlib import Path
+
+import pkg_resources as pkg
+import yaml
+from tqdm import tqdm
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+
+from utils.datasets import LoadImagesAndLabels
+from utils.datasets import img2label_paths
+from utils.general import check_dataset, check_file
+
+try:
+    import wandb
+
+    assert hasattr(wandb, '__version__')  # verify package import not local dir
+except (ImportError, AssertionError):
+    wandb = None
+    
+RANK = int(os.getenv('RANK', -1))
+WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
+
+
+def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX):
+    return from_string[len(prefix):]
+
+
+def check_wandb_config_file(data_config_file):
+    wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1))  # updated data.yaml path
+    if Path(wandb_config).is_file():
+        return wandb_config
+    return data_config_file
+
+
+def check_wandb_dataset(data_file):
+    is_trainset_wandb_artifact = False
+    is_valset_wandb_artifact = False
+    if check_file(data_file) and data_file.endswith('.yaml'):
+        with open(data_file, errors='ignore') as f:
+            data_dict = yaml.safe_load(f)
+        is_trainset_wandb_artifact = (isinstance(data_dict['train'], str) and
+                                      data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX))
+        is_valset_wandb_artifact = (isinstance(data_dict['val'], str) and
+                                    data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX))
+    if is_trainset_wandb_artifact or is_valset_wandb_artifact:
+        return data_dict
+    else:
+        return check_dataset(data_file)
+
+
+def get_run_info(run_path):
+    run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX))
+    run_id = run_path.stem
+    project = run_path.parent.stem
+    entity = run_path.parent.parent.stem
+    model_artifact_name = 'run_' + run_id + '_model'
+    return entity, project, run_id, model_artifact_name
+
+
+def check_wandb_resume(opt):
+    process_wandb_config_ddp_mode(opt) if RANK not in [-1, 0] else None
+    if isinstance(opt.resume, str):
+        if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+            if RANK not in [-1, 0]:  # For resuming DDP runs
+                entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
+                api = wandb.Api()
+                artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest')
+                modeldir = artifact.download()
+                opt.weights = str(Path(modeldir) / "last.pt")
+            return True
+    return None
+
+
+def process_wandb_config_ddp_mode(opt):
+    with open(check_file(opt.data), errors='ignore') as f:
+        data_dict = yaml.safe_load(f)  # data dict
+    train_dir, val_dir = None, None
+    if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX):
+        api = wandb.Api()
+        train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias)
+        train_dir = train_artifact.download()
+        train_path = Path(train_dir) / 'data/images/'
+        data_dict['train'] = str(train_path)
+
+    if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX):
+        api = wandb.Api()
+        val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias)
+        val_dir = val_artifact.download()
+        val_path = Path(val_dir) / 'data/images/'
+        data_dict['val'] = str(val_path)
+    if train_dir or val_dir:
+        ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml')
+        with open(ddp_data_path, 'w') as f:
+            yaml.safe_dump(data_dict, f)
+        opt.data = ddp_data_path
+
+
+class WandbLogger():
+    """Log training runs, datasets, models, and predictions to Weights & Biases.
+
+    This logger sends information to W&B at wandb.ai. By default, this information
+    includes hyperparameters, system configuration and metrics, model metrics,
+    and basic data metrics and analyses.
+
+    By providing additional command line arguments to train.py, datasets,
+    models and predictions can also be logged.
+
+    For more on how this logger is used, see the Weights & Biases documentation:
+    https://docs.wandb.com/guides/integrations/yolov5
+    """
+
+    def __init__(self, opt, run_id=None, job_type='Training'):
+        """
+        - Initialize WandbLogger instance
+        - Upload dataset if opt.upload_dataset is True
+        - Setup trainig processes if job_type is 'Training'
+
+        arguments:
+        opt (namespace) -- Commandline arguments for this run
+        run_id (str) -- Run ID of W&B run to be resumed
+        job_type (str) -- To set the job_type for this run 
+
+       """
+        # Pre-training routine --
+        self.job_type = job_type
+        self.wandb, self.wandb_run = wandb, None if not wandb else wandb.run
+        self.val_artifact, self.train_artifact = None, None
+        self.train_artifact_path, self.val_artifact_path = None, None
+        self.result_artifact = None
+        self.val_table, self.result_table = None, None
+        self.bbox_media_panel_images = []
+        self.val_table_path_map = None
+        self.max_imgs_to_log = 16
+        self.wandb_artifact_data_dict = None
+        self.data_dict = None
+        # It's more elegant to stick to 1 wandb.init call, but useful config data is overwritten in the WandbLogger's wandb.init call
+        if isinstance(opt.resume, str):  # checks resume from artifact
+            if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+                entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
+                model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name
+                assert wandb, 'install wandb to resume wandb runs'
+                # Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config
+                self.wandb_run = wandb.init(id=run_id,
+                                            project=project,
+                                            entity=entity,
+                                            resume='allow',
+                                            allow_val_change=True)
+                opt.resume = model_artifact_name
+        elif self.wandb:
+            self.wandb_run = wandb.init(config=opt,
+                                        resume="allow",
+                                        project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
+                                        entity=opt.entity,
+                                        name=opt.name if opt.name != 'exp' else None,
+                                        job_type=job_type,
+                                        id=run_id,
+                                        allow_val_change=True) if not wandb.run else wandb.run
+        if self.wandb_run:
+            if self.job_type == 'Training':
+                if opt.upload_dataset:
+                    if not opt.resume:
+                        self.wandb_artifact_data_dict = self.check_and_upload_dataset(opt)
+
+                if opt.resume:
+                    # resume from artifact
+                    if isinstance(opt.resume, str) and opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+                        self.data_dict = dict(self.wandb_run.config.data_dict)
+                    else:  # local resume
+                        self.data_dict = check_wandb_dataset(opt.data)
+                else:
+                    self.data_dict = check_wandb_dataset(opt.data)
+                    self.wandb_artifact_data_dict = self.wandb_artifact_data_dict or self.data_dict
+
+                    # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming.
+                    self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict},
+                                                 allow_val_change=True)
+                self.setup_training(opt)
+
+            if self.job_type == 'Dataset Creation':
+                self.data_dict = self.check_and_upload_dataset(opt)
+
+    def check_and_upload_dataset(self, opt):
+        """
+        Check if the dataset format is compatible and upload it as W&B artifact
+
+        arguments:
+        opt (namespace)-- Commandline arguments for current run
+
+        returns:
+        Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links.
+        """
+        assert wandb, 'Install wandb to upload dataset'
+        config_path = self.log_dataset_artifact(opt.data,
+                                                opt.single_cls,
+                                                'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
+        print("Created dataset config file ", config_path)
+        with open(config_path, errors='ignore') as f:
+            wandb_data_dict = yaml.safe_load(f)
+        return wandb_data_dict
+
+    def setup_training(self, opt):
+        """
+        Setup the necessary processes for training YOLO models:
+          - Attempt to download model checkpoint and dataset artifacts if opt.resume stats with WANDB_ARTIFACT_PREFIX
+          - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded
+          - Setup log_dict, initialize bbox_interval 
+
+        arguments:
+        opt (namespace) -- commandline arguments for this run
+
+        """
+        self.log_dict, self.current_epoch = {}, 0
+        self.bbox_interval = opt.bbox_interval
+        if isinstance(opt.resume, str):
+            modeldir, _ = self.download_model_artifact(opt)
+            if modeldir:
+                self.weights = Path(modeldir) / "last.pt"
+                config = self.wandb_run.config
+                opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp = str(
+                    self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs, \
+                                                                                                       config.hyp
+        data_dict = self.data_dict
+        if self.val_artifact is None:  # If --upload_dataset is set, use the existing artifact, don't download
+            self.train_artifact_path, self.train_artifact = self.download_dataset_artifact(data_dict.get('train'),
+                                                                                           opt.artifact_alias)
+            self.val_artifact_path, self.val_artifact = self.download_dataset_artifact(data_dict.get('val'),
+                                                                                       opt.artifact_alias)
+
+        if self.train_artifact_path is not None:
+            train_path = Path(self.train_artifact_path) / 'data/images/'
+            data_dict['train'] = str(train_path)
+        if self.val_artifact_path is not None:
+            val_path = Path(self.val_artifact_path) / 'data/images/'
+            data_dict['val'] = str(val_path)
+
+        if self.val_artifact is not None:
+            self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
+            self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
+            self.val_table = self.val_artifact.get("val")
+            if self.val_table_path_map is None:
+                self.map_val_table_path()
+        if opt.bbox_interval == -1:
+            self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1
+        train_from_artifact = self.train_artifact_path is not None and self.val_artifact_path is not None
+        # Update the the data_dict to point to local artifacts dir
+        if train_from_artifact:
+            self.data_dict = data_dict
+
+    def download_dataset_artifact(self, path, alias):
+        """
+        download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX
+
+        arguments:
+        path -- path of the dataset to be used for training
+        alias (str)-- alias of the artifact to be download/used for training
+
+        returns:
+        (str, wandb.Artifact) -- path of the downladed dataset and it's corresponding artifact object if dataset
+        is found otherwise returns (None, None)
+        """
+        if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX):
+            artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias)
+            dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\", "/"))
+            assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'"
+            datadir = dataset_artifact.download()
+            return datadir, dataset_artifact
+        return None, None
+
+    def download_model_artifact(self, opt):
+        """
+        download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX
+
+        arguments:
+        opt (namespace) -- Commandline arguments for this run
+        """
+        if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+            model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest")
+            assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist'
+            modeldir = model_artifact.download()
+            epochs_trained = model_artifact.metadata.get('epochs_trained')
+            total_epochs = model_artifact.metadata.get('total_epochs')
+            is_finished = total_epochs is None
+            assert not is_finished, 'training is finished, can only resume incomplete runs.'
+            return modeldir, model_artifact
+        return None, None
+
+    def log_model(self, path, opt, epoch, fitness_score, best_model=False):
+        """
+        Log the model checkpoint as W&B artifact
+
+        arguments:
+        path (Path)   -- Path of directory containing the checkpoints
+        opt (namespace) -- Command line arguments for this run
+        epoch (int)  -- Current epoch number
+        fitness_score (float) -- fitness score for current epoch 
+        best_model (boolean) -- Boolean representing if the current checkpoint is the best yet.
+        """
+        model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', type='model', metadata={
+            'original_url': str(path),
+            'epochs_trained': epoch + 1,
+            'save period': opt.save_period,
+            'project': opt.project,
+            'total_epochs': opt.epochs,
+            'fitness_score': fitness_score
+        })
+        model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
+        wandb.log_artifact(model_artifact,
+                           aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else ''])
+        print("Saving model artifact on epoch ", epoch + 1)
+
+    def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
+        """
+        Log the dataset as W&B artifact and return the new data file with W&B links
+
+        arguments:
+        data_file (str) -- the .yaml file with information about the dataset like - path, classes etc.
+        single_class (boolean)  -- train multi-class data as single-class
+        project (str) -- project name. Used to construct the artifact path
+        overwrite_config (boolean) -- overwrites the data.yaml file if set to true otherwise creates a new 
+        file with _wandb postfix. Eg -> data_wandb.yaml
+
+        returns:
+        the new .yaml file with artifact links. it can be used to start training directly from artifacts
+        """
+        self.data_dict = check_dataset(data_file)  # parse and check
+        data = dict(self.data_dict)
+        nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
+        names = {k: v for k, v in enumerate(names)}  # to index dictionary
+        self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
+            data['train'], rect=True, batch_size=1), names, name='train') if data.get('train') else None
+        self.val_artifact = self.create_dataset_table(LoadImagesAndLabels(
+            data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None
+        if data.get('train'):
+            data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train')
+        if data.get('val'):
+            data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val')
+        path = Path(data_file).stem
+        path = (path if overwrite_config else path + '_wandb') + '.yaml'  # updated data.yaml path
+        data.pop('download', None)
+        data.pop('path', None)
+        with open(path, 'w') as f:
+            yaml.safe_dump(data, f)
+
+        if self.job_type == 'Training':  # builds correct artifact pipeline graph
+            self.wandb_run.use_artifact(self.val_artifact)
+            self.wandb_run.use_artifact(self.train_artifact)
+            self.val_artifact.wait()
+            self.val_table = self.val_artifact.get('val')
+            self.map_val_table_path()
+        else:
+            self.wandb_run.log_artifact(self.train_artifact)
+            self.wandb_run.log_artifact(self.val_artifact)
+        return path
+
+    def map_val_table_path(self):
+        """
+        Map the validation dataset Table like name of file -> it's id in the W&B Table.
+        Useful for - referencing artifacts for evaluation.
+        """
+        self.val_table_path_map = {}
+        print("Mapping dataset")
+        for i, data in enumerate(tqdm(self.val_table.data)):
+            self.val_table_path_map[data[3]] = data[0]
+
+    def create_dataset_table(self, dataset, class_to_id, name='dataset'):
+        """
+        Create and return W&B artifact containing W&B Table of the dataset.
+
+        arguments:
+        dataset (LoadImagesAndLabels) -- instance of LoadImagesAndLabels class used to iterate over the data to build Table
+        class_to_id (dict(int, str)) -- hash map that maps class ids to labels
+        name (str) -- name of the artifact
+
+        returns:
+        dataset artifact to be logged or used
+        """
+        # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging
+        artifact = wandb.Artifact(name=name, type="dataset")
+        img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None
+        img_files = tqdm(dataset.img_files) if not img_files else img_files
+        for img_file in img_files:
+            if Path(img_file).is_dir():
+                artifact.add_dir(img_file, name='data/images')
+                labels_path = 'labels'.join(dataset.path.rsplit('images', 1))
+                artifact.add_dir(labels_path, name='data/labels')
+            else:
+                artifact.add_file(img_file, name='data/images/' + Path(img_file).name)
+                label_file = Path(img2label_paths([img_file])[0])
+                artifact.add_file(str(label_file),
+                                  name='data/labels/' + label_file.name) if label_file.exists() else None
+        table = wandb.Table(columns=["id", "train_image", "Classes", "name"])
+        class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()])
+        for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)):
+            box_data, img_classes = [], {}
+            for cls, *xywh in labels[:, 1:].tolist():
+                cls = int(cls)
+                box_data.append({"position": {"middle": [xywh[0], xywh[1]], "width": xywh[2], "height": xywh[3]},
+                                 "class_id": cls,
+                                 "box_caption": "%s" % (class_to_id[cls])})
+                img_classes[cls] = class_to_id[cls]
+            boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}}  # inference-space
+            table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), list(img_classes.values()),
+                           Path(paths).name)
+        artifact.add(table, name)
+        return artifact
+
+    def log_training_progress(self, predn, path, names):
+        """
+        Build evaluation Table. Uses reference from validation dataset table.
+
+        arguments:
+        predn (list): list of predictions in the native space in the format - [xmin, ymin, xmax, ymax, confidence, class]
+        path (str): local path of the current evaluation image 
+        names (dict(int, str)): hash map that maps class ids to labels
+        """
+        class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()])
+        box_data = []
+        total_conf = 0
+        for *xyxy, conf, cls in predn.tolist():
+            if conf >= 0.25:
+                box_data.append(
+                    {"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+                     "class_id": int(cls),
+                     "box_caption": "%s %.3f" % (names[cls], conf),
+                     "scores": {"class_score": conf},
+                     "domain": "pixel"})
+                total_conf = total_conf + conf
+        boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
+        id = self.val_table_path_map[Path(path).name]
+        self.result_table.add_data(self.current_epoch,
+                                   id,
+                                   self.val_table.data[id][1],
+                                   wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set),
+                                   total_conf / max(1, len(box_data))
+                                   )
+
+    def val_one_image(self, pred, predn, path, names, im):
+        """
+        Log validation data for one image. updates the result Table if validation dataset is uploaded and log bbox media panel
+
+        arguments:
+        pred (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class]
+        predn (list): list of predictions in the native space - [xmin, ymin, xmax, ymax, confidence, class]
+        path (str): local path of the current evaluation image 
+        """
+        if self.val_table and self.result_table:  # Log Table if Val dataset is uploaded as artifact
+            self.log_training_progress(predn, path, names)
+
+        if len(self.bbox_media_panel_images) < self.max_imgs_to_log and self.current_epoch > 0:
+            if self.current_epoch % self.bbox_interval == 0:
+                box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+                             "class_id": int(cls),
+                             "box_caption": "%s %.3f" % (names[cls], conf),
+                             "scores": {"class_score": conf},
+                             "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
+                boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
+                self.bbox_media_panel_images.append(wandb.Image(im, boxes=boxes, caption=path.name))
+
+    def log(self, log_dict):
+        """
+        save the metrics to the logging dictionary
+
+        arguments:
+        log_dict (Dict) -- metrics/media to be logged in current step
+        """
+        if self.wandb_run:
+            for key, value in log_dict.items():
+                self.log_dict[key] = value
+
+    def end_epoch(self, best_result=False):
+        """
+        commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
+
+        arguments:
+        best_result (boolean): Boolean representing if the result of this evaluation is best or not
+        """
+        if self.wandb_run:
+            with all_logging_disabled():
+                if self.bbox_media_panel_images:
+                    self.log_dict["Bounding Box Debugger/Images"] = self.bbox_media_panel_images
+                wandb.log(self.log_dict)
+                self.log_dict = {}
+                self.bbox_media_panel_images = []
+            if self.result_artifact:
+                self.result_artifact.add(self.result_table, 'result')
+                wandb.log_artifact(self.result_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch),
+                                                                  ('best' if best_result else '')])
+
+                wandb.log({"evaluation": self.result_table})
+                self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
+                self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
+
+    def finish_run(self):
+        """
+        Log metrics if any and finish the current W&B run
+        """
+        if self.wandb_run:
+            if self.log_dict:
+                with all_logging_disabled():
+                    wandb.log(self.log_dict)
+            wandb.run.finish()
+
+
+@contextmanager
+def all_logging_disabled(highest_level=logging.CRITICAL):
+    """ source - https://gist.github.com/simon-weber/7853144
+    A context manager that will prevent any logging messages triggered during the body from being processed.
+    :param highest_level: the maximum logging level in use.
+      This would only need to be changed if a custom level greater than CRITICAL is defined.
+    """
+    previous_level = logging.root.manager.disable
+    logging.disable(highest_level)
+    try:
+        yield
+    finally:
+        logging.disable(previous_level)

yolov5processor/utils/loss.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Loss functions
+"""
+
+import torch
+import torch.nn as nn
+
+from yolov5processor.utils.metrics import bbox_iou
+from yolov5processor.utils.torch_utils import is_parallel
+
+
+def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
+    # return positive, negative label smoothing BCE targets
+    return 1.0 - 0.5 * eps, 0.5 * eps
+
+
+class BCEBlurWithLogitsLoss(nn.Module):
+    # BCEwithLogitLoss() with reduced missing label effects.
+    def __init__(self, alpha=0.05):
+        super(BCEBlurWithLogitsLoss, self).__init__()
+        self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none')  # must be nn.BCEWithLogitsLoss()
+        self.alpha = alpha
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+        pred = torch.sigmoid(pred)  # prob from logits
+        dx = pred - true  # reduce only missing label effects
+        # dx = (pred - true).abs()  # reduce missing label and false label effects
+        alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
+        loss *= alpha_factor
+        return loss.mean()
+
+
+class FocalLoss(nn.Module):
+    # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+        super(FocalLoss, self).__init__()
+        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
+        self.gamma = gamma
+        self.alpha = alpha
+        self.reduction = loss_fcn.reduction
+        self.loss_fcn.reduction = 'none'  # required to apply FL to each element
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+        # p_t = torch.exp(-loss)
+        # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability
+
+        # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
+        pred_prob = torch.sigmoid(pred)  # prob from logits
+        p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
+        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+        modulating_factor = (1.0 - p_t) ** self.gamma
+        loss *= alpha_factor * modulating_factor
+
+        if self.reduction == 'mean':
+            return loss.mean()
+        elif self.reduction == 'sum':
+            return loss.sum()
+        else:  # 'none'
+            return loss
+
+
+class QFocalLoss(nn.Module):
+    # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+        super(QFocalLoss, self).__init__()
+        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
+        self.gamma = gamma
+        self.alpha = alpha
+        self.reduction = loss_fcn.reduction
+        self.loss_fcn.reduction = 'none'  # required to apply FL to each element
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+
+        pred_prob = torch.sigmoid(pred)  # prob from logits
+        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+        modulating_factor = torch.abs(true - pred_prob) ** self.gamma
+        loss *= alpha_factor * modulating_factor
+
+        if self.reduction == 'mean':
+            return loss.mean()
+        elif self.reduction == 'sum':
+            return loss.sum()
+        else:  # 'none'
+            return loss
+
+
+class ComputeLoss:
+    # Compute losses
+    def __init__(self, model, autobalance=False):
+        self.sort_obj_iou = False
+        device = next(model.parameters()).device  # get model device
+        h = model.hyp  # hyperparameters
+
+        # Define criteria
+        BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
+        BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
+
+        # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
+        self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0))  # positive, negative BCE targets
+
+        # Focal loss
+        g = h['fl_gamma']  # focal loss gamma
+        if g > 0:
+            BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
+
+        det = model.module.model[-1] if is_parallel(model) else model.model[-1]  # Detect() module
+        self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02])  # P3-P7
+        self.ssi = list(det.stride).index(16) if autobalance else 0  # stride 16 index
+        self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
+        for k in 'na', 'nc', 'nl', 'anchors':
+            setattr(self, k, getattr(det, k))
+
+    def __call__(self, p, targets):  # predictions, targets, model
+        device = targets.device
+        lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
+        tcls, tbox, indices, anchors = self.build_targets(p, targets)  # targets
+
+        # Losses
+        for i, pi in enumerate(p):  # layer index, layer predictions
+            b, a, gj, gi = indices[i]  # image, anchor, gridy, gridx
+            tobj = torch.zeros_like(pi[..., 0], device=device)  # target obj
+
+            n = b.shape[0]  # number of targets
+            if n:
+                ps = pi[b, a, gj, gi]  # prediction subset corresponding to targets
+
+                # Regression
+                pxy = ps[:, :2].sigmoid() * 2. - 0.5
+                pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
+                pbox = torch.cat((pxy, pwh), 1)  # predicted box
+                iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
+                lbox += (1.0 - iou).mean()  # iou loss
+
+                # Objectness
+                score_iou = iou.detach().clamp(0).type(tobj.dtype)
+                if self.sort_obj_iou:
+                    sort_id = torch.argsort(score_iou)
+                    b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id]
+                tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou  # iou ratio
+
+                # Classification
+                if self.nc > 1:  # cls loss (only if multiple classes)
+                    t = torch.full_like(ps[:, 5:], self.cn, device=device)  # targets
+                    t[range(n), tcls[i]] = self.cp
+                    lcls += self.BCEcls(ps[:, 5:], t)  # BCE
+
+                # Append targets to text file
+                # with open('targets.txt', 'a') as file:
+                #     [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
+
+            obji = self.BCEobj(pi[..., 4], tobj)
+            lobj += obji * self.balance[i]  # obj loss
+            if self.autobalance:
+                self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
+
+        if self.autobalance:
+            self.balance = [x / self.balance[self.ssi] for x in self.balance]
+        lbox *= self.hyp['box']
+        lobj *= self.hyp['obj']
+        lcls *= self.hyp['cls']
+        bs = tobj.shape[0]  # batch size
+
+        return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()
+
+    def build_targets(self, p, targets):
+        # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
+        na, nt = self.na, targets.shape[0]  # number of anchors, targets
+        tcls, tbox, indices, anch = [], [], [], []
+        gain = torch.ones(7, device=targets.device)  # normalized to gridspace gain
+        ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
+        targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2)  # append anchor indices
+
+        g = 0.5  # bias
+        off = torch.tensor([[0, 0],
+                            [1, 0], [0, 1], [-1, 0], [0, -1],  # j,k,l,m
+                            # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
+                            ], device=targets.device).float() * g  # offsets
+
+        for i in range(self.nl):
+            anchors = self.anchors[i]
+            gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  # xyxy gain
+
+            # Match targets to anchors
+            t = targets * gain
+            if nt:
+                # Matches
+                r = t[:, :, 4:6] / anchors[:, None]  # wh ratio
+                j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t']  # compare
+                # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
+                t = t[j]  # filter
+
+                # Offsets
+                gxy = t[:, 2:4]  # grid xy
+                gxi = gain[[2, 3]] - gxy  # inverse
+                j, k = ((gxy % 1. < g) & (gxy > 1.)).T
+                l, m = ((gxi % 1. < g) & (gxi > 1.)).T
+                j = torch.stack((torch.ones_like(j), j, k, l, m))
+                t = t.repeat((5, 1, 1))[j]
+                offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
+            else:
+                t = targets[0]
+                offsets = 0
+
+            # Define
+            b, c = t[:, :2].long().T  # image, class
+            gxy = t[:, 2:4]  # grid xy
+            gwh = t[:, 4:6]  # grid wh
+            gij = (gxy - offsets).long()
+            gi, gj = gij.T  # grid xy indices
+
+            # Append
+            a = t[:, 6].long()  # anchor indices
+            indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))  # image, anchor, grid indices
+            tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
+            anch.append(anchors[a])  # anchors
+            tcls.append(c)  # class
+
+        return tcls, tbox, indices, anch

yolov5processor/utils/metrics.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Model validation metrics
+"""
+
+import math
+import warnings
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import numpy as np
+import torch
+
+
+def fitness(x):
+    # Model fitness as a weighted combination of metrics
+    w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
+    return (x[:, :4] * w).sum(1)
+
+
+def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
+    """ Compute the average precision, given the recall and precision curves.
+    Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
+    # Arguments
+        tp:  True positives (nparray, nx1 or nx10).
+        conf:  Objectness value from 0-1 (nparray).
+        pred_cls:  Predicted object classes (nparray).
+        target_cls:  True object classes (nparray).
+        plot:  Plot precision-recall curve at mAP@0.5
+        save_dir:  Plot save directory
+    # Returns
+        The average precision as computed in py-faster-rcnn.
+    """
+
+    # Sort by objectness
+    i = np.argsort(-conf)
+    tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
+
+    # Find unique classes
+    unique_classes = np.unique(target_cls)
+    nc = unique_classes.shape[0]  # number of classes, number of detections
+
+    # Create Precision-Recall curve and compute AP for each class
+    px, py = np.linspace(0, 1, 1000), []  # for plotting
+    ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
+    for ci, c in enumerate(unique_classes):
+        i = pred_cls == c
+        n_l = (target_cls == c).sum()  # number of labels
+        n_p = i.sum()  # number of predictions
+
+        if n_p == 0 or n_l == 0:
+            continue
+        else:
+            # Accumulate FPs and TPs
+            fpc = (1 - tp[i]).cumsum(0)
+            tpc = tp[i].cumsum(0)
+
+            # Recall
+            recall = tpc / (n_l + 1e-16)  # recall curve
+            r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0)  # negative x, xp because xp decreases
+
+            # Precision
+            precision = tpc / (tpc + fpc)  # precision curve
+            p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1)  # p at pr_score
+
+            # AP from recall-precision curve
+            for j in range(tp.shape[1]):
+                ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
+                if plot and j == 0:
+                    py.append(np.interp(px, mrec, mpre))  # precision at mAP@0.5
+
+    # Compute F1 (harmonic mean of precision and recall)
+    f1 = 2 * p * r / (p + r + 1e-16)
+    if plot:
+        plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
+        plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
+        plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
+        plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
+
+    i = f1.mean(0).argmax()  # max F1 index
+    return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
+
+
+def compute_ap(recall, precision):
+    """ Compute the average precision, given the recall and precision curves
+    # Arguments
+        recall:    The recall curve (list)
+        precision: The precision curve (list)
+    # Returns
+        Average precision, precision curve, recall curve
+    """
+
+    # Append sentinel values to beginning and end
+    mrec = np.concatenate(([0.0], recall, [1.0]))
+    mpre = np.concatenate(([1.0], precision, [0.0]))
+
+    # Compute the precision envelope
+    mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
+
+    # Integrate area under curve
+    method = 'interp'  # methods: 'continuous', 'interp'
+    if method == 'interp':
+        x = np.linspace(0, 1, 101)  # 101-point interp (COCO)
+        ap = np.trapz(np.interp(x, mrec, mpre), x)  # integrate
+    else:  # 'continuous'
+        i = np.where(mrec[1:] != mrec[:-1])[0]  # points where x axis (recall) changes
+        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])  # area under curve
+
+    return ap, mpre, mrec
+
+
+class ConfusionMatrix:
+    # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
+    def __init__(self, nc, conf=0.25, iou_thres=0.45):
+        self.matrix = np.zeros((nc + 1, nc + 1))
+        self.nc = nc  # number of classes
+        self.conf = conf
+        self.iou_thres = iou_thres
+
+    def process_batch(self, detections, labels):
+        """
+        Return intersection-over-union (Jaccard index) of boxes.
+        Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+        Arguments:
+            detections (Array[N, 6]), x1, y1, x2, y2, conf, class
+            labels (Array[M, 5]), class, x1, y1, x2, y2
+        Returns:
+            None, updates confusion matrix accordingly
+        """
+        detections = detections[detections[:, 4] > self.conf]
+        gt_classes = labels[:, 0].int()
+        detection_classes = detections[:, 5].int()
+        iou = box_iou(labels[:, 1:], detections[:, :4])
+
+        x = torch.where(iou > self.iou_thres)
+        if x[0].shape[0]:
+            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
+            if x[0].shape[0] > 1:
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+        else:
+            matches = np.zeros((0, 3))
+
+        n = matches.shape[0] > 0
+        m0, m1, _ = matches.transpose().astype(np.int16)
+        for i, gc in enumerate(gt_classes):
+            j = m0 == i
+            if n and sum(j) == 1:
+                self.matrix[detection_classes[m1[j]], gc] += 1  # correct
+            else:
+                self.matrix[self.nc, gc] += 1  # background FP
+
+        if n:
+            for i, dc in enumerate(detection_classes):
+                if not any(m1 == i):
+                    self.matrix[dc, self.nc] += 1  # background FN
+
+    def matrix(self):
+        return self.matrix
+
+    def plot(self, normalize=True, save_dir='', names=()):
+        try:
+            import seaborn as sn
+
+            array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-6) if normalize else 1)  # normalize columns
+            array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)
+
+            fig = plt.figure(figsize=(12, 9), tight_layout=True)
+            sn.set(font_scale=1.0 if self.nc < 50 else 0.8)  # for label size
+            labels = (0 < len(names) < 99) and len(names) == self.nc  # apply names to ticklabels
+            with warnings.catch_warnings():
+                warnings.simplefilter('ignore')  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
+                sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
+                           xticklabels=names + ['background FP'] if labels else "auto",
+                           yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
+            fig.axes[0].set_xlabel('True')
+            fig.axes[0].set_ylabel('Predicted')
+            fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
+            plt.close()
+        except Exception as e:
+            print(f'WARNING: ConfusionMatrix plot failure: {e}')
+
+    def print(self):
+        for i in range(self.nc + 1):
+            print(' '.join(map(str, self.matrix[i])))
+
+
+def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
+    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
+    box2 = box2.T
+
+    # Get the coordinates of bounding boxes
+    if x1y1x2y2:  # x1, y1, x2, y2 = box1
+        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+    else:  # transform from xywh to xyxy
+        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
+        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
+        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
+        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
+
+    # Intersection area
+    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
+            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
+
+    # Union Area
+    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
+    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
+    union = w1 * h1 + w2 * h2 - inter + eps
+
+    iou = inter / union
+    if GIoU or DIoU or CIoU:
+        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
+        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
+        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
+            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
+            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
+                    (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squared
+            if DIoU:
+                return iou - rho2 / c2  # DIoU
+            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
+                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
+                with torch.no_grad():
+                    alpha = v / (v - iou + (1 + eps))
+                return iou - (rho2 / c2 + v * alpha)  # CIoU
+        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
+            c_area = cw * ch + eps  # convex area
+            return iou - (c_area - union) / c_area  # GIoU
+    else:
+        return iou  # IoU
+
+
+def box_iou(box1, box2):
+    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+    """
+    Return intersection-over-union (Jaccard index) of boxes.
+    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+    Arguments:
+        box1 (Tensor[N, 4])
+        box2 (Tensor[M, 4])
+    Returns:
+        iou (Tensor[N, M]): the NxM matrix containing the pairwise
+            IoU values for every element in boxes1 and boxes2
+    """
+
+    def box_area(box):
+        # box = 4xn
+        return (box[2] - box[0]) * (box[3] - box[1])
+
+    area1 = box_area(box1.T)
+    area2 = box_area(box2.T)
+
+    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
+    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
+    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+def bbox_ioa(box1, box2, eps=1E-7):
+    """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2
+    box1:       np.array of shape(4)
+    box2:       np.array of shape(nx4)
+    returns:    np.array of shape(n)
+    """
+
+    box2 = box2.transpose()
+
+    # Get the coordinates of bounding boxes
+    b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+    b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+
+    # Intersection area
+    inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
+                 (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
+
+    # box2 area
+    box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps
+
+    # Intersection over box2 area
+    return inter_area / box2_area
+
+
+def wh_iou(wh1, wh2):
+    # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
+    wh1 = wh1[:, None]  # [N,1,2]
+    wh2 = wh2[None]  # [1,M,2]
+    inter = torch.min(wh1, wh2).prod(2)  # [N,M]
+    return inter / (wh1.prod(2) + wh2.prod(2) - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+# Plots ----------------------------------------------------------------------------------------------------------------
+
+def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
+    # Precision-recall curve
+    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
+    py = np.stack(py, axis=1)
+
+    if 0 < len(names) < 21:  # display per-class legend if < 21 classes
+        for i, y in enumerate(py.T):
+            ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}')  # plot(recall, precision)
+    else:
+        ax.plot(px, py, linewidth=1, color='grey')  # plot(recall, precision)
+
+    ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
+    ax.set_xlabel('Recall')
+    ax.set_ylabel('Precision')
+    ax.set_xlim(0, 1)
+    ax.set_ylim(0, 1)
+    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
+    fig.savefig(Path(save_dir), dpi=250)
+    plt.close()
+
+
+def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
+    # Metric-confidence curve
+    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
+
+    if 0 < len(names) < 21:  # display per-class legend if < 21 classes
+        for i, y in enumerate(py):
+            ax.plot(px, y, linewidth=1, label=f'{names[i]}')  # plot(confidence, metric)
+    else:
+        ax.plot(px, py.T, linewidth=1, color='grey')  # plot(confidence, metric)
+
+    y = py.mean(0)
+    ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
+    ax.set_xlabel(xlabel)
+    ax.set_ylabel(ylabel)
+    ax.set_xlim(0, 1)
+    ax.set_ylim(0, 1)
+    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
+    fig.savefig(Path(save_dir), dpi=250)
+    plt.close()

yolov5processor/utils/plots.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Plotting utils
+"""
+
+import math
+import os
+from copy import copy
+from pathlib import Path
+
+import cv2
+import matplotlib
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sn
+import torch
+from PIL import Image, ImageDraw, ImageFont
+
+from yolov5processor.utils.general import user_config_dir, is_ascii, is_chinese, xywh2xyxy, xyxy2xywh
+from yolov5processor.utils.metrics import fitness
+
+# Settings
+CONFIG_DIR = user_config_dir()  # Ultralytics settings dir
+RANK = int(os.getenv('RANK', -1))
+matplotlib.rc('font', **{'size': 11})
+matplotlib.use('Agg')  # for writing to files only
+
+
+class Colors:
+    # Ultralytics color palette https://ultralytics.com/
+    def __init__(self):
+        # hex = matplotlib.colors.TABLEAU_COLORS.values()
+        hex = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
+               '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
+        self.palette = [self.hex2rgb('#' + c) for c in hex]
+        self.n = len(self.palette)
+
+    def __call__(self, i, bgr=False):
+        c = self.palette[int(i) % self.n]
+        return (c[2], c[1], c[0]) if bgr else c
+
+    @staticmethod
+    def hex2rgb(h):  # rgb order (PIL)
+        return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
+
+
+colors = Colors()  # create instance for 'from utils.plots import colors'
+
+
+def check_font(font='Arial.ttf', size=10):
+    # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary
+    font = Path(font)
+    font = font if font.exists() else (CONFIG_DIR / font.name)
+    try:
+        return ImageFont.truetype(str(font) if font.exists() else font.name, size)
+    except Exception as e:  # download if missing
+        url = "https://ultralytics.com/assets/" + font.name
+        print(f'Downloading {url} to {font}...')
+        torch.hub.download_url_to_file(url, str(font), progress=False)
+        return ImageFont.truetype(str(font), size)
+
+
+class Annotator:
+    if RANK in (-1, 0):
+        check_font()  # download TTF if necessary
+
+    # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations
+    def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
+        assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
+        self.pil = pil or not is_ascii(example) or is_chinese(example)
+        if self.pil:  # use PIL
+            self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
+            self.draw = ImageDraw.Draw(self.im)
+            self.font = check_font(font='Arial.Unicode.ttf' if is_chinese(example) else font,
+                                   size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
+        else:  # use cv2
+            self.im = im
+        self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2)  # line width
+
+    def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
+        # Add one xyxy box to image with label
+        if self.pil or not is_ascii(label):
+            self.draw.rectangle(box, width=self.lw, outline=color)  # box
+            if label:
+                w, h = self.font.getsize(label)  # text width, height
+                outside = box[1] - h >= 0  # label fits outside box
+                self.draw.rectangle([box[0],
+                                     box[1] - h if outside else box[1],
+                                     box[0] + w + 1,
+                                     box[1] + 1 if outside else box[1] + h + 1], fill=color)
+                # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
+                self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
+        else:  # cv2
+            p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
+            cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
+            if label:
+                tf = max(self.lw - 1, 1)  # font thickness
+                w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0]  # text width, height
+                outside = p1[1] - h - 3 >= 0  # label fits outside box
+                p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
+                cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
+                cv2.putText(self.im, label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), 0, self.lw / 3, txt_color,
+                            thickness=tf, lineType=cv2.LINE_AA)
+
+    def rectangle(self, xy, fill=None, outline=None, width=1):
+        # Add rectangle to image (PIL-only)
+        self.draw.rectangle(xy, fill, outline, width)
+
+    def text(self, xy, text, txt_color=(255, 255, 255)):
+        # Add text to image (PIL-only)
+        w, h = self.font.getsize(text)  # text width, height
+        self.draw.text((xy[0], xy[1] - h + 1), text, fill=txt_color, font=self.font)
+
+    def result(self):
+        # Return annotated image as array
+        return np.asarray(self.im)
+
+
+def hist2d(x, y, n=100):
+    # 2d histogram used in labels.png and evolve.png
+    xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
+    hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges))
+    xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1)
+    yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1)
+    return np.log(hist[xidx, yidx])
+
+
+def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5):
+    from scipy.signal import butter, filtfilt
+
+    # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy
+    def butter_lowpass(cutoff, fs, order):
+        nyq = 0.5 * fs
+        normal_cutoff = cutoff / nyq
+        return butter(order, normal_cutoff, btype='low', analog=False)
+
+    b, a = butter_lowpass(cutoff, fs, order=order)
+    return filtfilt(b, a, data)  # forward-backward filter
+
+
+def output_to_target(output):
+    # Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
+    targets = []
+    for i, o in enumerate(output):
+        for *box, conf, cls in o.cpu().numpy():
+            targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
+    return np.array(targets)
+
+
+def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=1920, max_subplots=16):
+    # Plot image grid with labels
+    if isinstance(images, torch.Tensor):
+        images = images.cpu().float().numpy()
+    if isinstance(targets, torch.Tensor):
+        targets = targets.cpu().numpy()
+    if np.max(images[0]) <= 1:
+        images *= 255.0  # de-normalise (optional)
+    bs, _, h, w = images.shape  # batch size, _, height, width
+    bs = min(bs, max_subplots)  # limit plot images
+    ns = np.ceil(bs ** 0.5)  # number of subplots (square)
+
+    # Build Image
+    mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8)  # init
+    for i, im in enumerate(images):
+        if i == max_subplots:  # if last batch has fewer images than we expect
+            break
+        x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
+        im = im.transpose(1, 2, 0)
+        mosaic[y:y + h, x:x + w, :] = im
+
+    # Resize (optional)
+    scale = max_size / ns / max(h, w)
+    if scale < 1:
+        h = math.ceil(scale * h)
+        w = math.ceil(scale * w)
+        mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h)))
+
+    # Annotate
+    fs = int((h + w) * ns * 0.01)  # font size
+    annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True)
+    for i in range(i + 1):
+        x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
+        annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2)  # borders
+        if paths:
+            annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
+        if len(targets) > 0:
+            ti = targets[targets[:, 0] == i]  # image targets
+            boxes = xywh2xyxy(ti[:, 2:6]).T
+            classes = ti[:, 1].astype('int')
+            labels = ti.shape[1] == 6  # labels if no conf column
+            conf = None if labels else ti[:, 6]  # check for confidence presence (label vs pred)
+
+            if boxes.shape[1]:
+                if boxes.max() <= 1.01:  # if normalized with tolerance 0.01
+                    boxes[[0, 2]] *= w  # scale to pixels
+                    boxes[[1, 3]] *= h
+                elif scale < 1:  # absolute coords need scale if image scales
+                    boxes *= scale
+            boxes[[0, 2]] += x
+            boxes[[1, 3]] += y
+            for j, box in enumerate(boxes.T.tolist()):
+                cls = classes[j]
+                color = colors(cls)
+                cls = names[cls] if names else cls
+                if labels or conf[j] > 0.25:  # 0.25 conf thresh
+                    label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}'
+                    annotator.box_label(box, label, color=color)
+    annotator.im.save(fname)  # save
+
+
+def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''):
+    # Plot LR simulating training for full epochs
+    optimizer, scheduler = copy(optimizer), copy(scheduler)  # do not modify originals
+    y = []
+    for _ in range(epochs):
+        scheduler.step()
+        y.append(optimizer.param_groups[0]['lr'])
+    plt.plot(y, '.-', label='LR')
+    plt.xlabel('epoch')
+    plt.ylabel('LR')
+    plt.grid()
+    plt.xlim(0, epochs)
+    plt.ylim(0)
+    plt.savefig(Path(save_dir) / 'LR.png', dpi=200)
+    plt.close()
+
+
+def plot_val_txt():  # from utils.plots import *; plot_val()
+    # Plot val.txt histograms
+    x = np.loadtxt('val.txt', dtype=np.float32)
+    box = xyxy2xywh(x[:, :4])
+    cx, cy = box[:, 0], box[:, 1]
+
+    fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True)
+    ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0)
+    ax.set_aspect('equal')
+    plt.savefig('hist2d.png', dpi=300)
+
+    fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True)
+    ax[0].hist(cx, bins=600)
+    ax[1].hist(cy, bins=600)
+    plt.savefig('hist1d.png', dpi=200)
+
+
+def plot_targets_txt():  # from utils.plots import *; plot_targets_txt()
+    # Plot targets.txt histograms
+    x = np.loadtxt('targets.txt', dtype=np.float32).T
+    s = ['x targets', 'y targets', 'width targets', 'height targets']
+    fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
+    ax = ax.ravel()
+    for i in range(4):
+        ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
+        ax[i].legend()
+        ax[i].set_title(s[i])
+    plt.savefig('targets.jpg', dpi=200)
+
+
+def plot_val_study(file='', dir='', x=None):  # from utils.plots import *; plot_val_study()
+    # Plot file=study.txt generated by val.py (or plot all study*.txt in dir)
+    save_dir = Path(file).parent if file else Path(dir)
+    plot2 = False  # plot additional results
+    if plot2:
+        ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)[1].ravel()
+
+    fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
+    # for f in [save_dir / f'study_coco_{x}.txt' for x in ['yolov5n6', 'yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]:
+    for f in sorted(save_dir.glob('study*.txt')):
+        y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
+        x = np.arange(y.shape[1]) if x is None else np.array(x)
+        if plot2:
+            s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_preprocess (ms/img)', 't_inference (ms/img)', 't_NMS (ms/img)']
+            for i in range(7):
+                ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
+                ax[i].set_title(s[i])
+
+        j = y[3].argmax() + 1
+        ax2.plot(y[5, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
+                 label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
+
+    ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
+             'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
+
+    ax2.grid(alpha=0.2)
+    ax2.set_yticks(np.arange(20, 60, 5))
+    ax2.set_xlim(0, 57)
+    ax2.set_ylim(25, 55)
+    ax2.set_xlabel('GPU Speed (ms/img)')
+    ax2.set_ylabel('COCO AP val')
+    ax2.legend(loc='lower right')
+    f = save_dir / 'study.png'
+    print(f'Saving {f}...')
+    plt.savefig(f, dpi=300)
+
+
+def plot_labels(labels, names=(), save_dir=Path('')):
+    # plot dataset labels
+    print('Plotting labels... ')
+    c, b = labels[:, 0], labels[:, 1:].transpose()  # classes, boxes
+    nc = int(c.max() + 1)  # number of classes
+    x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
+
+    # seaborn correlogram
+    sn.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
+    plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
+    plt.close()
+
+    # matplotlib labels
+    matplotlib.use('svg')  # faster
+    ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
+    y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
+    # [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)]  # update colors bug #3195
+    ax[0].set_ylabel('instances')
+    if 0 < len(names) < 30:
+        ax[0].set_xticks(range(len(names)))
+        ax[0].set_xticklabels(names, rotation=90, fontsize=10)
+    else:
+        ax[0].set_xlabel('classes')
+    sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
+    sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
+
+    # rectangles
+    labels[:, 1:3] = 0.5  # center
+    labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
+    img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
+    for cls, *box in labels[:1000]:
+        ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls))  # plot
+    ax[1].imshow(img)
+    ax[1].axis('off')
+
+    for a in [0, 1, 2, 3]:
+        for s in ['top', 'right', 'left', 'bottom']:
+            ax[a].spines[s].set_visible(False)
+
+    plt.savefig(save_dir / 'labels.jpg', dpi=200)
+    matplotlib.use('Agg')
+    plt.close()
+
+
+def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
+    # Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
+    ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
+    s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
+    files = list(Path(save_dir).glob('frames*.txt'))
+    for fi, f in enumerate(files):
+        try:
+            results = np.loadtxt(f, ndmin=2).T[:, 90:-30]  # clip first and last rows
+            n = results.shape[1]  # number of rows
+            x = np.arange(start, min(stop, n) if stop else n)
+            results = results[:, x]
+            t = (results[0] - results[0].min())  # set t0=0s
+            results[0] = x
+            for i, a in enumerate(ax):
+                if i < len(results):
+                    label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
+                    a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
+                    a.set_title(s[i])
+                    a.set_xlabel('time (s)')
+                    # if fi == len(files) - 1:
+                    #     a.set_ylim(bottom=0)
+                    for side in ['top', 'right']:
+                        a.spines[side].set_visible(False)
+                else:
+                    a.remove()
+        except Exception as e:
+            print('Warning: Plotting error for %s; %s' % (f, e))
+    ax[1].legend()
+    plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
+
+
+def plot_evolve(evolve_csv='path/to/evolve.csv'):  # from utils.plots import *; plot_evolve()
+    # Plot evolve.csv hyp evolution results
+    evolve_csv = Path(evolve_csv)
+    data = pd.read_csv(evolve_csv)
+    keys = [x.strip() for x in data.columns]
+    x = data.values
+    f = fitness(x)
+    j = np.argmax(f)  # max fitness index
+    plt.figure(figsize=(10, 12), tight_layout=True)
+    matplotlib.rc('font', **{'size': 8})
+    for i, k in enumerate(keys[7:]):
+        v = x[:, 7 + i]
+        mu = v[j]  # best single result
+        plt.subplot(6, 5, i + 1)
+        plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
+        plt.plot(mu, f.max(), 'k+', markersize=15)
+        plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9})  # limit to 40 characters
+        if i % 5 != 0:
+            plt.yticks([])
+        print('%15s: %.3g' % (k, mu))
+    f = evolve_csv.with_suffix('.png')  # filename
+    plt.savefig(f, dpi=200)
+    plt.close()
+    print(f'Saved {f}')
+
+
+def plot_results(file='path/to/results.csv', dir=''):
+    # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv')
+    save_dir = Path(file).parent if file else Path(dir)
+    fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
+    ax = ax.ravel()
+    files = list(save_dir.glob('results*.csv'))
+    assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.'
+    for fi, f in enumerate(files):
+        try:
+            data = pd.read_csv(f)
+            s = [x.strip() for x in data.columns]
+            x = data.values[:, 0]
+            for i, j in enumerate([1, 2, 3, 4, 5, 8, 9, 10, 6, 7]):
+                y = data.values[:, j]
+                # y[y == 0] = np.nan  # don't show zero values
+                ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=8)
+                ax[i].set_title(s[j], fontsize=12)
+                # if j in [8, 9, 10]:  # share train and val loss y axes
+                #     ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
+        except Exception as e:
+            print(f'Warning: Plotting error for {f}: {e}')
+    ax[1].legend()
+    fig.savefig(save_dir / 'results.png', dpi=200)
+    plt.close()
+
+
+def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
+    """
+    x:              Features to be visualized
+    module_type:    Module type
+    stage:          Module stage within model
+    n:              Maximum number of feature maps to plot
+    save_dir:       Directory to save results
+    """
+    if 'Detect' not in module_type:
+        batch, channels, height, width = x.shape  # batch, channels, height, width
+        if height > 1 and width > 1:
+            f = f"stage{stage}_{module_type.split('.')[-1]}_features.png"  # filename
+
+            blocks = torch.chunk(x[0].cpu(), channels, dim=0)  # select batch index 0, block by channels
+            n = min(n, channels)  # number of plots
+            fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True)  # 8 rows x n/8 cols
+            ax = ax.ravel()
+            plt.subplots_adjust(wspace=0.05, hspace=0.05)
+            for i in range(n):
+                ax[i].imshow(blocks[i].squeeze())  # cmap='gray'
+                ax[i].axis('off')
+
+            print(f'Saving {save_dir / f}... ({n}/{channels})')
+            plt.savefig(save_dir / f, dpi=300, bbox_inches='tight')
+            plt.close()

yolov5processor/utils/torch_utils.py

+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+PyTorch utils
+"""
+
+import datetime
+import logging
+import math
+import os
+import platform
+import subprocess
+import time
+from contextlib import contextmanager
+from copy import deepcopy
+from pathlib import Path
+
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision
+
+try:
+    import thop  # for FLOPs computation
+except ImportError:
+    thop = None
+
+LOGGER = logging.getLogger(__name__)
+
+
+@contextmanager
+def torch_distributed_zero_first(local_rank: int):
+    """
+    Decorator to make all processes in distributed training wait for each local_master to do something.
+    """
+    if local_rank not in [-1, 0]:
+        dist.barrier(device_ids=[local_rank])
+    yield
+    if local_rank == 0:
+        dist.barrier(device_ids=[0])
+
+
+def date_modified(path=__file__):
+    # return human-readable file modification date, i.e. '2021-3-26'
+    t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime)
+    return f'{t.year}-{t.month}-{t.day}'
+
+
+def git_describe(path=Path(__file__).parent):  # path must be a directory
+    # return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe
+    s = f'git -C {path} describe --tags --long --always'
+    try:
+        return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1]
+    except subprocess.CalledProcessError as e:
+        return ''  # not a git repository
+
+
+def select_device(device='', batch_size=None):
+    # device = 'cpu' or '0' or '0,1,2,3'
+    s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} '  # string
+    device = str(device).strip().lower().replace('cuda:', '')  # to string, 'cuda:0' to '0'
+    cpu = device == 'cpu'
+    if cpu:
+        os.environ['CUDA_VISIBLE_DEVICES'] = '-1'  # force torch.cuda.is_available() = False
+    elif device:  # non-cpu device requested
+        os.environ['CUDA_VISIBLE_DEVICES'] = device  # set environment variable
+        assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested'  # check availability
+
+    cuda = not cpu and torch.cuda.is_available()
+    if cuda:
+        devices = device.split(',') if device else '0'  # range(torch.cuda.device_count())  # i.e. 0,1,6,7
+        n = len(devices)  # device count
+        if n > 1 and batch_size:  # check batch_size is divisible by device_count
+            assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
+        space = ' ' * (len(s) + 1)
+        for i, d in enumerate(devices):
+            p = torch.cuda.get_device_properties(i)
+            s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n"  # bytes to MB
+    else:
+        s += 'CPU\n'
+
+    LOGGER.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s)  # emoji-safe
+    return torch.device('cuda:0' if cuda else 'cpu')
+
+
+def time_sync():
+    # pytorch-accurate time
+    if torch.cuda.is_available():
+        torch.cuda.synchronize()
+    return time.time()
+
+
+def profile(input, ops, n=10, device=None):
+    # YOLOv5 speed/memory/FLOPs profiler
+    #
+    # Usage:
+    #     input = torch.randn(16, 3, 640, 640)
+    #     m1 = lambda x: x * torch.sigmoid(x)
+    #     m2 = nn.SiLU()
+    #     profile(input, [m1, m2], n=100)  # profile over 100 iterations
+
+    results = []
+    logging.basicConfig(format="%(message)s", level=logging.INFO)
+    device = device or select_device()
+    print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
+          f"{'input':>24s}{'output':>24s}")
+
+    for x in input if isinstance(input, list) else [input]:
+        x = x.to(device)
+        x.requires_grad = True
+        for m in ops if isinstance(ops, list) else [ops]:
+            m = m.to(device) if hasattr(m, 'to') else m  # device
+            m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m
+            tf, tb, t = 0., 0., [0., 0., 0.]  # dt forward, backward
+            try:
+                flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2  # GFLOPs
+            except:
+                flops = 0
+
+            try:
+                for _ in range(n):
+                    t[0] = time_sync()
+                    y = m(x)
+                    t[1] = time_sync()
+                    try:
+                        _ = (sum([yi.sum() for yi in y]) if isinstance(y, list) else y).sum().backward()
+                        t[2] = time_sync()
+                    except Exception as e:  # no backward method
+                        print(e)
+                        t[2] = float('nan')
+                    tf += (t[1] - t[0]) * 1000 / n  # ms per op forward
+                    tb += (t[2] - t[1]) * 1000 / n  # ms per op backward
+                mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0  # (GB)
+                s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
+                s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
+                p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0  # parameters
+                print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}')
+                results.append([p, flops, mem, tf, tb, s_in, s_out])
+            except Exception as e:
+                print(e)
+                results.append(None)
+            torch.cuda.empty_cache()
+    return results
+
+
+def is_parallel(model):
+    # Returns True if model is of type DP or DDP
+    return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
+
+
+def de_parallel(model):
+    # De-parallelize a model: returns single-GPU model if model is of type DP or DDP
+    return model.module if is_parallel(model) else model
+
+
+def intersect_dicts(da, db, exclude=()):
+    # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
+    return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
+
+
+def initialize_weights(model):
+    for m in model.modules():
+        t = type(m)
+        if t is nn.Conv2d:
+            pass  # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+        elif t is nn.BatchNorm2d:
+            m.eps = 1e-3
+            m.momentum = 0.03
+        elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
+            m.inplace = True
+
+
+def find_modules(model, mclass=nn.Conv2d):
+    # Finds layer indices matching module class 'mclass'
+    return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
+
+
+def sparsity(model):
+    # Return global model sparsity
+    a, b = 0., 0.
+    for p in model.parameters():
+        a += p.numel()
+        b += (p == 0).sum()
+    return b / a
+
+
+def prune(model, amount=0.3):
+    # Prune model to requested global sparsity
+    import torch.nn.utils.prune as prune
+    print('Pruning model... ', end='')
+    for name, m in model.named_modules():
+        if isinstance(m, nn.Conv2d):
+            prune.l1_unstructured(m, name='weight', amount=amount)  # prune
+            prune.remove(m, 'weight')  # make permanent
+    print(' %.3g global sparsity' % sparsity(model))
+
+
+def fuse_conv_and_bn(conv, bn):
+    # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
+    fusedconv = nn.Conv2d(conv.in_channels,
+                          conv.out_channels,
+                          kernel_size=conv.kernel_size,
+                          stride=conv.stride,
+                          padding=conv.padding,
+                          groups=conv.groups,
+                          bias=True).requires_grad_(False).to(conv.weight.device)
+
+    # prepare filters
+    w_conv = conv.weight.clone().view(conv.out_channels, -1)
+    w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
+    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
+
+    # prepare spatial bias
+    b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
+    b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
+    fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
+
+    return fusedconv
+
+
+def model_info(model, verbose=False, img_size=640):
+    # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
+    n_p = sum(x.numel() for x in model.parameters())  # number parameters
+    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
+    if verbose:
+        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
+        for i, (name, p) in enumerate(model.named_parameters()):
+            name = name.replace('module_list.', '')
+            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
+                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
+
+    try:  # FLOPs
+        from thop import profile
+        stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32
+        img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device)  # input
+        flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2  # stride GFLOPs
+        img_size = img_size if isinstance(img_size, list) else [img_size, img_size]  # expand if int/float
+        fs = ', %.1f GFLOPs' % (flops * img_size[0] / stride * img_size[1] / stride)  # 640x640 GFLOPs
+    except (ImportError, Exception):
+        fs = ''
+
+    LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
+
+
+def load_classifier(name='resnet101', n=2):
+    # Loads a pretrained model reshaped to n-class output
+    model = torchvision.models.__dict__[name](pretrained=True)
+
+    # ResNet model properties
+    # input_size = [3, 224, 224]
+    # input_space = 'RGB'
+    # input_range = [0, 1]
+    # mean = [0.485, 0.456, 0.406]
+    # std = [0.229, 0.224, 0.225]
+
+    # Reshape output to n classes
+    filters = model.fc.weight.shape[1]
+    model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
+    model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
+    model.fc.out_features = n
+    return model
+
+
+def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
+    # scales img(bs,3,y,x) by ratio constrained to gs-multiple
+    if ratio == 1.0:
+        return img
+    else:
+        h, w = img.shape[2:]
+        s = (int(h * ratio), int(w * ratio))  # new size
+        img = F.interpolate(img, size=s, mode='bilinear', align_corners=False)  # resize
+        if not same_shape:  # pad/crop img
+            h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
+        return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447)  # value = imagenet mean
+
+
+def copy_attr(a, b, include=(), exclude=()):
+    # Copy attributes from b to a, options to only include [...] and to exclude [...]
+    for k, v in b.__dict__.items():
+        if (len(include) and k not in include) or k.startswith('_') or k in exclude:
+            continue
+        else:
+            setattr(a, k, v)
+
+
+class EarlyStopping:
+    # YOLOv5 simple early stopper
+    def __init__(self, patience=30):
+        self.best_fitness = 0.0  # i.e. mAP
+        self.best_epoch = 0
+        self.patience = patience or float('inf')  # epochs to wait after fitness stops improving to stop
+        self.possible_stop = False  # possible stop may occur next epoch
+
+    def __call__(self, epoch, fitness):
+        if fitness >= self.best_fitness:  # >= 0 to allow for early zero-fitness stage of training
+            self.best_epoch = epoch
+            self.best_fitness = fitness
+        delta = epoch - self.best_epoch  # epochs without improvement
+        self.possible_stop = delta >= (self.patience - 1)  # possible stop may occur next epoch
+        stop = delta >= self.patience  # stop training if patience exceeded
+        if stop:
+            LOGGER.info(f'EarlyStopping patience {self.patience} exceeded, stopping training.')
+        return stop
+
+
+class ModelEMA:
+    """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
+    Keep a moving average of everything in the model state_dict (parameters and buffers).
+    This is intended to allow functionality like
+    https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
+    A smoothed version of the weights is necessary for some training schemes to perform well.
+    This class is sensitive where it is initialized in the sequence of model init,
+    GPU assignment and distributed training wrappers.
+    """
+
+    def __init__(self, model, decay=0.9999, updates=0):
+        # Create EMA
+        self.ema = deepcopy(model.module if is_parallel(model) else model).eval()  # FP32 EMA
+        # if next(model.parameters()).device.type != 'cpu':
+        #     self.ema.half()  # FP16 EMA
+        self.updates = updates  # number of EMA updates
+        self.decay = lambda x: decay * (1 - math.exp(-x / 2000))  # decay exponential ramp (to help early epochs)
+        for p in self.ema.parameters():
+            p.requires_grad_(False)
+
+    def update(self, model):
+        # Update EMA parameters
+        with torch.no_grad():
+            self.updates += 1
+            d = self.decay(self.updates)
+
+            msd = model.module.state_dict() if is_parallel(model) else model.state_dict()  # model state_dict
+            for k, v in self.ema.state_dict().items():
+                if v.dtype.is_floating_point:
+                    v *= d
+                    v += (1. - d) * msd[k].detach()
+
+    def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
+        # Update EMA attributes
+        copy_attr(self.ema, model, include, exclude)