I know I'm a junior in the Machine Learning field. so maybe this project is not perfect. Please let me know if I'm wrong. I used Pytorch library and OpenCV for for making this project.
This is brief of my project: 1- Downloaded fasterrcnn_mobilenet_v3_large_320_fpn 2- Used OpenCV to seprate frames from video. 3- Passed each frame to pre_process_image function. 4- Feeded each frame to the mobilenet model and get result. 5- Aggregation all frames to a video file.