ValueError: Cannot feed value of shape (3, 3, 512, 256) for Tensor 'G_synthesis_3/64x64/Conv0_up/weight/new_value:0', which has shape '(3, 3, 512, 512)'

when I was using ffhq-res256-mirror-paper256-noaug.pkl pretrained weight , it can not be loaded then I print the layers_information:

pretrained weight : rGs =

rG =

G_main Params OutputShape WeightShape

---

latents_in - (?, 512) -
labels_in - (?, 0) -
G_mapping/Normalize - (?, 512) -
G_mapping/Dense0 262656 (?, 512) (512, 512)
G_mapping/Dense1 262656 (?, 512) (512, 512)
G_mapping/Dense2 262656 (?, 512) (512, 512)
G_mapping/Dense3 262656 (?, 512) (512, 512)
G_mapping/Dense4 262656 (?, 512) (512, 512)
G_mapping/Dense5 262656 (?, 512) (512, 512)
G_mapping/Dense6 262656 (?, 512) (512, 512)
G_mapping/Dense7 262656 (?, 512) (512, 512)
G_mapping/Broadcast - (?, 14, 512) -
dlatent_avg - (512,) -
Truncation/Lerp - (?, 14, 512) -
G_synthesis/4x4/Const 8192 (?, 512, 4, 4) (1, 512, 4, 4)
G_synthesis/4x4/Conv 2622465 (?, 512, 4, 4) (3, 3, 512, 512) G_synthesis/4x4/ToRGB 264195 (?, 3, 4, 4) (1, 1, 512, 3)
G_synthesis/8x8/Conv0_up 2622465 (?, 512, 8, 8) (3, 3, 512, 512) G_synthesis/8x8/Conv1 2622465 (?, 512, 8, 8) (3, 3, 512, 512) G_synthesis/8x8/Upsample - (?, 3, 8, 8) -
G_synthesis/8x8/ToRGB 264195 (?, 3, 8, 8) (1, 1, 512, 3)
G_synthesis/16x16/Conv0_up 2622465 (?, 512, 16, 16) (3, 3, 512, 512) G_synthesis/16x16/Conv1 2622465 (?, 512, 16, 16) (3, 3, 512, 512) G_synthesis/16x16/Upsample - (?, 3, 16, 16) -
G_synthesis/16x16/ToRGB 264195 (?, 3, 16, 16) (1, 1, 512, 3)
G_synthesis/32x32/Conv0_up 2622465 (?, 512, 32, 32) (3, 3, 512, 512) G_synthesis/32x32/Conv1 2622465 (?, 512, 32, 32) (3, 3, 512, 512) G_synthesis/32x32/Upsample - (?, 3, 32, 32) -
G_synthesis/32x32/ToRGB 264195 (?, 3, 32, 32) (1, 1, 512, 3)
G_synthesis/64x64/Conv0_up 1442561 (?, 256, 64, 64) (3, 3, 512, 256) G_synthesis/64x64/Conv1 721409 (?, 256, 64, 64) (3, 3, 256, 256) G_synthesis/64x64/Upsample - (?, 3, 64, 64) -
G_synthesis/64x64/ToRGB 132099 (?, 3, 64, 64) (1, 1, 256, 3)
G_synthesis/128x128/Conv0_up 426369 (?, 128, 128, 128) (3, 3, 256, 128) G_synthesis/128x128/Conv1 213249 (?, 128, 128, 128) (3, 3, 128, 128) G_synthesis/128x128/Upsample - (?, 3, 128, 128) -
G_synthesis/128x128/ToRGB 66051 (?, 3, 128, 128) (1, 1, 128, 3)
G_synthesis/256x256/Conv0_up 139457 (?, 64, 256, 256) (3, 3, 128, 64) G_synthesis/256x256/Conv1 69761 (?, 64, 256, 256) (3, 3, 64, 64)
G_synthesis/256x256/Upsample - (?, 3, 256, 256) -
G_synthesis/256x256/ToRGB 33027 (?, 3, 256, 256) (1, 1, 64, 3)

---

Total 24767458

build G network :

G =

G Params OutputShape WeightShape

---

latents_in - (?, 512) -
labels_in - (?, 0) -
G_mapping/Normalize - (?, 512) -
G_mapping/Dense0 262656 (?, 512) (512, 512)
G_mapping/Dense1 262656 (?, 512) (512, 512)
G_mapping/Dense2 262656 (?, 512) (512, 512)
G_mapping/Dense3 262656 (?, 512) (512, 512)
G_mapping/Dense4 262656 (?, 512) (512, 512)
G_mapping/Dense5 262656 (?, 512) (512, 512)
G_mapping/Dense6 262656 (?, 512) (512, 512)
G_mapping/Dense7 262656 (?, 512) (512, 512)
G_mapping/Broadcast - (?, 14, 512) -
dlatent_avg - (512,) -
Truncation/Lerp - (?, 14, 512) -
G_synthesis/4x4/Const 8192 (?, 512, 4, 4) (1, 512, 4, 4)
G_synthesis/4x4/Conv 2622465 (?, 512, 4, 4) (3, 3, 512, 512) G_synthesis/4x4/ToRGB 264195 (?, 3, 4, 4) (1, 1, 512, 3)
G_synthesis/8x8/Conv0_up 2622465 (?, 512, 8, 8) (3, 3, 512, 512) G_synthesis/8x8/Conv1 2622465 (?, 512, 8, 8) (3, 3, 512, 512) G_synthesis/8x8/Upsample - (?, 3, 8, 8) -
G_synthesis/8x8/ToRGB 264195 (?, 3, 8, 8) (1, 1, 512, 3)
G_synthesis/16x16/Conv0_up 2622465 (?, 512, 16, 16) (3, 3, 512, 512) G_synthesis/16x16/Conv1 2622465 (?, 512, 16, 16) (3, 3, 512, 512) G_synthesis/16x16/Upsample - (?, 3, 16, 16) -
G_synthesis/16x16/ToRGB 264195 (?, 3, 16, 16) (1, 1, 512, 3)
G_synthesis/32x32/Conv0_up 2622465 (?, 512, 32, 32) (3, 3, 512, 512) G_synthesis/32x32/Conv1 2622465 (?, 512, 32, 32) (3, 3, 512, 512) G_synthesis/32x32/Upsample - (?, 3, 32, 32) -
G_synthesis/32x32/ToRGB 264195 (?, 3, 32, 32) (1, 1, 512, 3)
G_synthesis/64x64/Conv0_up 2622465 (?, 512, 64, 64) (3, 3, 512, 512) G_synthesis/64x64/Conv1 2622465 (?, 512, 64, 64) (3, 3, 512, 512) G_synthesis/64x64/Upsample - (?, 3, 64, 64) -
G_synthesis/64x64/ToRGB 264195 (?, 3, 64, 64) (1, 1, 512, 3)
G_synthesis/128x128/Conv0_up 1442561 (?, 256, 128, 128) (3, 3, 512, 256) G_synthesis/128x128/Conv1 721409 (?, 256, 128, 128) (3, 3, 256, 256) G_synthesis/128x128/Upsample - (?, 3, 128, 128) -
G_synthesis/128x128/ToRGB 132099 (?, 3, 128, 128) (1, 1, 256, 3)
G_synthesis/256x256/Conv0_up 426369 (?, 128, 256, 256) (3, 3, 256, 128) G_synthesis/256x256/Conv1 213249 (?, 128, 256, 256) (3, 3, 128, 128) G_synthesis/256x256/Upsample - (?, 3, 256, 256) -
G_synthesis/256x256/ToRGB 66051 (?, 3, 256, 256) (1, 1, 128, 3)

---

Total 30034338

The two networks are not the same！！

Hello,

This is not really an Issue but I wasn't sure where to put this question.

I was wondering if you would do a version for StyleGan2_ada with PyTorch

Hello,

is there a way to freeze the generator?

I added this, but it does not seem to work. I basically did the same you did to freeze the discriminator.

if freezedG is not None:
    assert isinstance(freezedG, int)
    if not freezedG >= 0:
        raise UserError('--freezed must be non-negative')
    desc += f'-freezed{freezedG:g}'
    args.G_args.freeze_layers = freezed

I am also wondering why the generator was left without parameters to freeze it.

Hi, thanks for the notebook!

I have difficulties getting it to run, as it is missing the module "training" and I also don't seem to be able to install it with pip.

Do you have an idea how this could be fixed?

Thank you!

Hey there. thank you so much for this notebook, it is exactly what I've been looking for!

I can't seem to get it to recognize that my dataset is in the google drive and I'm not sure why. In cell [14] I keep getting the message 'Upload your images dataset as [path]', which is the exact path of my dataset. I have no idea what I could be doing wrong here; I've quadruple checked that both paths are the same. Has anyone else run into this issue?

Thanks!

Hi, I'm trying to save both qlatent and dlatent vectors along with the generated images for to find latent directions later. Can when i save the Zs vectors it only has shape 1,512 so i'm assuming its qlatent. So how does one also gets the dlatent vector also?

Hi I have managed to get my local gpu connected, but when I use my local gpu I can't run most of the cells that work fine when i use Googles gpu, the cells all turn red and don't run on my local gpu. Any tips on how to get that to work?