Kyuchul Lee

You have already that code (last few lines in video_swap.py)

On question #1 The ID loss uses cosine similarity (applied in the face recognition network family a.k.a ArcFace) This is to increase the similarity between the two images in terms...

@usmancheema89 I'm sorry for the late reply. There are no special restrictions. Instead of the model previously provided by the authors, we used the model deployed in the path below...

Hi, If your detector output None, the there is one choice the resize your detection size from 640 to smaller one. It can improve your detection results.

I found same issue when the training is initiated. But after some iterations are processed, the inference results will be get better.