AliaksandrSiarohin

I don't get what you want. Probably demo.py

ffmpeg -i result.mp4 -vf scale=400:200 result2.mp4

I only run inference after 100 epochs.

Is it working on colab?

The dataset is pretty imbalanced, so one identity could have ~100 videos, while other could have 1. But to be honest I implement this from the very beginning and did...

That is weird usually I get more or less the same results. At least in the terms of loss.

I did not try and it is hard to say what will work better. But my intuition was that with this we focus our prediction near the keypoint. Indeed why...

If you remove flag relative from you will see.

What do you mean, what results? In the notebook it is called absolute motion, you can check it out.

This a derivative of the first equation in this image, why are you asking about T(St