Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Even <a href="https://github.com/bes-dev/MobileStyleGAN.pytorch/blob/a9776ff8f05a868b2

`compute_mean_style` method generates gray image about mobilestylegan.pytorch HOT 6 CLOSED

RahulBhalley commented on July 24, 2024

`compute_mean_style` method generates gray image

from mobilestylegan.pytorch.

Comments (6)

bes-dev commented on July 24, 2024 1

@RahulBhalley our code doesn't load pre-trained student automatically, you should load it on your side. Please, look at this sample of code:

MobileStyleGAN.pytorch/demo.py

Line 14 in a9776ff

if args.ckpt != "":

from mobilestylegan.pytorch.

bes-dev commented on July 24, 2024

@RahulBhalley did you load pre-trained checkpoint?

from mobilestylegan.pytorch.

RahulBhalley commented on July 24, 2024

@bes-dev after running the following lines of code

cfg = load_cfg("configs/mobile_stylegan_ffhq.json")
distiller = Distiller(cfg)

I get the following output.

load mapping network...
load pretrained model: stylegan2_ffhq_config_f_mapping_network.ckpt...
Computing MD5: /tmp/stylegan2_ffhq_config_f_mapping_network.ckpt
MD5 matches: /tmp/stylegan2_ffhq_config_f_mapping_network.ckpt
load synthesis network...
load pretrained model: stylegan2_ffhq_config_f_synthesis_network.ckpt...
Computing MD5: /tmp/stylegan2_ffhq_config_f_synthesis_network.ckpt
MD5 matches: /tmp/stylegan2_ffhq_config_f_synthesis_network.ckpt
/Users/codeboy/Freelancing/SocialKit/face-app/restyle-encoder-light/venv/lib/python3.9/site-packages/torchvision/models/inception.py:80: FutureWarning: The default weight initialization of inception_v3 will be changed in future releases of torchvision. If you wish to keep the old behavior (which leads to long initialization times due to scipy/scipy#11299), please set init_weights=True.
  warnings.warn('The default weight initialization of inception_v3 will be changed in future releases of '

It looks like the checkpoints are loaded (for mapping_net also).

from mobilestylegan.pytorch.

RahulBhalley commented on July 24, 2024

I tried using distiller.style_mean but still I get gray image.

out = distiller.student(distiller.style_mean)['img']

from mobilestylegan.pytorch.

RahulBhalley commented on July 24, 2024

Even truncation trick doesn't produce face image (but just gray).

var = torch.randn(1, 512)
style = distiller.mapping_net(var)
style = distiller.style_mean + 0.5 * (style - distiller.style_mean)
out = distiller.student(style)['img']