Is there a problem with the output of the discriminator?

[ripperthejack]

The generator is pre-trained and I used the dual discriminator just like:

ag3d_discriminator = legacy.load_network_pkl(f)['D'].to(args.device)
output = G.only_synthesis(ws=ws, c=c, truncation_psi=truncation)
full_logit = ag3d_discriminator.D_image(output,c)

but i got a low confidence around -10 , is that normal?

[shash29-dev]

Hi,
There is something it seems regarding discriminators.
I tried --
Training from Scratch: fake_depths and fake_images look alright (similar to sampled smpl pose). As training proceeds, fake_depths become total black and white. images go full background-- (white)
Training from provided weights: fake_depths and fake_images look alright (similar to sampled smpl pose, and realistic). As training proceeds, both deteriorate towards ---> fake_depths become total black and white. images go full background-- (white)

I speculate the reason behind it, may be a discriminator issue driving the generator crazy?

[ripperthejack]

hey bro , have you successfully reproduced this model ?