AttGAN-PyTorch

AttGAN-PyTorch copied to clipboard

Why no instancenorm in fcs?

1

you said:"No instancenorm in fcs in source code, which is different from paper." Is it the same as the tensorflow version by the author? Is it get better than having...

daizigege

Attributes don't change

3

Hi, Thank you very much for sharing this helpful code. I am training the AttGAN with CelebA image size 128, 1GPU, batch size 32. After about 60K iterations I don't...

morkap

what are shortcut_layers and inject_layers in generator layer

2

Hi, Many thanks for providing your code publicly. Could you please explain what are shortcut_layers and inject_layers in generator? Thank you.

Sepideh-Rezaeirad

Can you provide the train graphs from tensorboard?

1

Thanks for this great code!

sdahan12

Could you provide the pretrained model of discriminator of 256_shortcut1_inject1_none_hq?

3

There is no pretrained model of 256_shortcut1_inject1_none_hq.

liang23333

AttGAN RuntimeERROR:Sizes of tensors must match except in dimension 1

5

Hi, when I use Pytorch-1.7 to train AttGAN from scratch, a RuntimeERROR appears. There are more details: Traceback (most recent call last): File "train.py", line 161, in errD = attgan.trainD(img_a,...

GuanlinLee

Bug in Encoding and Decoding Parameters

3

Hi I've been messing around with this code and found an error. If I use these params in the AttGAN class ``` def __init__(self, enc_dim=64, enc_layers=6, enc_norm_fn='batchnorm', enc_acti_fn='lrelu', dec_dim=64, dec_layers=6,...

EoinKenny

What's the meaning of inject_int and thres_int?

1

why use extra attr_a_ and attr_b_ for attr_a and attr_b?

Ksky001

Pretrained model doesn't seem to have necessary file

2

Hey, The pretrained model doesn't have necessary '*pth' [https://github.com/elvisyjlin/AttGAN-PyTorch/blob/master/utils.py#L14](url) Model - 128_shortcut1_inject1_none Can you help out here?

Varshul

Pretrained model doesn't acess

1

xuezhongcailian