heykeetae Self-Attention-GAN issues

heykeetae / Self-Attention-GAN

Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

2.53k stars 475 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Thor harsh patch 1-1

#68 thor-harsh opened 7 months ago
1
the download.sh can't use

#67 hanjiahe1999 opened 7 months ago
1
How can I determine if the model has converged?

#66 suprola1017 opened 8 months ago
0
我长期研究和改进GAN，如果对GAN或者深度学习感兴趣的可以联系我，联系方式，wechat: lovedaixiaobaby

#65 anshen666 opened 1 year ago
0
Add examples to work with audio files as well

#64 tipycalFlow opened 1 year ago
0
Trying the Self-Attention-GAN with dog images

#63 liku-amare opened 1 year ago
0
self.gamma*out considered as "in place" operation

#62 NGluna03 opened 2 years ago
0
Confused by self-attention layer positioning in Discriminator

#61 AceVenturos opened 3 years ago
1
Negative self.gamma parameter??

#60 navalkishoremehta95 closed 3 years ago
0
torch.bmm(), CUDA out of memory.

#59 lyricgoal opened 3 years ago
3
How to make the repo available for input image of 256x256 size?

#58 25th-engineer closed 3 years ago
1
the meaning of Gamma in Attention model

#57 hank19960918 opened 3 years ago
3
1

#56 yangyu615 opened 3 years ago
0
RuntimeError: cublas runtime error : the GPU program failed to execute at /pytorch/aten/src/THC/THCBlas.cu:450

#55 RokiaAbdeen opened 3 years ago
0
The code is different from the original paper

#54 lmisssunl opened 3 years ago
2
Adding Tensorboard

#53 Avashist1998 opened 4 years ago
0
dropbox link missing

#52 NisargBhatt73 opened 4 years ago
1
UnboundLocalError: local variable 'dataset' referenced before assignment

#51 1184022880com opened 4 years ago
4
Missing one 1x1 conv on output from attention layer?

#50 harrygcoppock closed 4 years ago
4
model.py is working only for imsize=64

#49 franknb opened 4 years ago
1
detach fake image when updating the discriminator

#48 kam1107 opened 4 years ago
0
About negative gamma

#47 SeokjuLee closed 4 years ago
10
dataset structure

#46 Tianshuo-Xu opened 4 years ago
1
About：AttributeError: 'Conv2d' object has no attribute 'weight'

#45 15732031137 opened 4 years ago
8
about visualization code

#44 amiltonwong opened 5 years ago
0
Weird Error while using multi GPU.

#43 AIprogrammer opened 5 years ago
0
AttributeError: module 'torch.nn' has no attribute 'ModuleDict'

#42 ykshi closed 5 years ago
0
Softmax

#41 abelmouhcine closed 5 years ago
0
is there no activation on self attn layer?

#40 caffeinism closed 3 years ago
2
Cannot Download CelebA dataset

#39 StellaLI-0501 opened 5 years ago
4
256*256

#38 Ahalang opened 5 years ago
2
permute twice?

#37 aflyingnoob opened 5 years ago
1
Variable image size.

#36 caffeinism closed 5 years ago
0
test class missing

#35 enochkan opened 5 years ago
3
FID and IS

#34 Avyukth opened 5 years ago
2
class conditional batch norm not implemented

#33 djl11 opened 5 years ago
0
Gumbel Softmax?

#32 emited opened 5 years ago
0
Spectral norm on Generator

#31 dougsouza opened 5 years ago
0
new data set

#30 asifkyni opened 5 years ago
4
I add self_Attn to another network , but it causes cuda error : out of memory

#29 cooodeKnight opened 6 years ago
6
I want to train the model by cifar-10 using batch size=128, but there is negative gamma emerged. Is it influence the results generated?

#28 long-username opened 6 years ago
0
i think the implementation of WGAN-GP loss is wrong

#27 civilman628 opened 6 years ago
1
Hello,heykeetae,has this implement implied conditional batch normalization? It seems that not support multi-class image generation.

#26 mrj-taffy opened 6 years ago
0
Has this implementation reproduced the results of the original paper?

#25 cmsflash closed 6 years ago
2
How to use in 3D conv?

#24 guanfaqian opened 6 years ago
0
In the 1*1*1 convlution, should we need to set the bias/b = 0?

#23 winwinJJiang opened 6 years ago
0
Which Loss for CelebA Results?

#22 tegillis closed 6 years ago
0
d_iters seems not being used

#21 r06922019 opened 6 years ago
0
hinge loss

#20 IPNUISTlegal opened 6 years ago
1
About the attention map

#19 o0t1ng0o opened 6 years ago
11