Inaccurate Result When Running OpenVINO™ Object Detection Python* Demo with Yolo-v3-Tf

• Downloaded yolo-v3-tf via Model Downloader:
  ./downloader.py --name yolo-v3-tf

• Converted the model via Model Optimizer:
  python3 ./model_optimizer/mo.py --input_model /home/user/intel/openvino_2021.4.752/deployment_tools/open_model_zoo/models/public/yolo-v3-tf/yolo-v3.pb --input_shape "[1, 416, 416, 3]" --reverse_input_channels

• Unable to detect objects when using the converted model with Object Detection Python* Demo:
  python3 open_model_zoo/demos/object_detection_demo/python/object_detection_demo.py -d CPU -i /home/user/Downloads/car-detection.mp4 -m /home/user/intel/openvino_2021.4.752/deployment_tools/open_model_zoo/models/public/yolo-v3-tf/yolo-v3.xml -at yolo -o output_%03d.jpg

Use Model Converter to convert OpenVINO™ Toolkit Public Pre-Trained Models.