PyTorch_YOWO
PyTorch_YOWO copied to clipboard
This is the result after 5 eopch of iteration,The video's accuracy is not there. But frame's accuracy is about the same as YOWO-Plus,So I'm a little puzzled and hope to...
I find your work great but I downloaded the YOWO-NANO weights from github and still receiving this error.  
Why is the reproduction accuracy not as good as in the paper?
This repo has no requirements.txt
if I want to do custom training. should I mark each and every human in a frame with some class label? in my case (suppose try to build a running...
Thank you for sharing your awesome repo ! I just wonder when I run `evalutate_video_map` function, I encountered `No such file or directory: ` error. Could you plz how to...
Thank you for sharing your awesome works ! When I train a model about the JHMDB-21, the difference of frame-mAP is too high. For example, 65 frame-mAP ~ 74 frame-mAP....