-
Notifications
You must be signed in to change notification settings - Fork 7
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Stage 1 - training losses - todo contrastive_loss #14
Comments
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! |
thanks for pointing this out. I fix later. |
i draft this - yet to test it out. so much flux - needs stabilising. I look at the patchgan stuff |
warped_driving_frame:torch.Size([3, 129, 129]) on my training branch - i implement and fix - but now the warped / cropped image is small.... |
https://github.com/johndpope/MegaPortrait-hack/blob/main/train.py#L196
adding any of the others hits a bug with gradients.
The text was updated successfully, but these errors were encountered: