Stage 1 - training losses - todo contrastive_loss

[johndpope]

https://github.com/johndpope/MegaPortrait-hack/blob/main/train.py#L196

adding any of the others hits a bug with gradients.

[Jie-zju]

Have you noticed "losses are calculated using only foreground regions" mentioned in Paper? I tried implement the network (include somewhat different from paper ) and train it. However, just use loss on all images for training seems fail, since the training stage is not stable. I think "losses are calculated using only foreground regions" May Be Important ! Please attention on it!

[johndpope]

thanks for pointing this out. I fix later.

[johndpope]

i draft this - yet to test it out.
https://github.com/johndpope/MegaPortrait-hack/pull/21/files

so much flux - needs stabilising.
fyi @robinchm

I look at the patchgan stuff

[johndpope]

warped_driving_frame:torch.Size([3, 129, 129])

on my training branch - i implement and fix - but now the warped / cropped image is small....
i can make it bigger - or I have to work out how the network can accept smaller images....
not sure.
https://github.com/johndpope/MegaPortrait-hack/tree/feat/14-training

[johndpope]

some progress.