aitorzip PyTorch-CycleGAN issues

aitorzip / PyTorch-CycleGAN

A clean and readable Pytorch implementation of CycleGAN

https://arxiv.org/abs/1703.10593

GNU General Public License v3.0

1.19k stars 283 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Traceback (most recent call last): File "E:\Desktop\PyTorch-CycleGAN-master\test", line 73, in <module> real_A = Variable(input_A.copy_(batch['A'])) RuntimeError: The size of tensor a (256) must match the size of tensor b (1920) at non-singleton dimension 3

#45 Chopper525 opened 2 months ago
0
Beginners' question: Is there a way to use a pre-trained model, or that I have to train it myself?

#44 UrielV1 opened 1 year ago
0
picture size

#43 trash-boy opened 1 year ago
1
UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimiz er.step()` before `lr_scheduler.step()`. Failure to do this will result in PyTorch skipping the first value of the learning rate schedule.

#42 guanjingshuo opened 1 year ago
0
Can the results same as the official implement?

#41 Ssakura-go opened 1 year ago
1
New: modernized repository

#40 arnauddhaene opened 2 years ago
0
about identity loss

#39 karim-moon closed 2 years ago
1
Pls tell me why derive the discriminator loss function w.r.t. the label rather than the input data.

#38 KeatsHao opened 2 years ago
0
question about train

#37 xiaofeng-c opened 3 years ago
1
RuntimeError: The expanded size of the tensor (1224) must match the existing size (370) at non-singleton dimension 2

#36 yanjinwei143 opened 3 years ago
0
RuntimeError: The expanded size of the tensor (1) must match the existing size (3) at non-singleton dimension 0

#35 chenmw269 opened 3 years ago
2
Training problems：Setting up a new session

#34 chenmw269 closed 3 years ago
1
UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum.

#33 JimberZ opened 3 years ago
8
Training did not converge,how to change the parameters?plz!

#32 Emir-Liu opened 3 years ago
1
why not fix D while updating G?

#31 XiaoyuShi97 closed 3 years ago
1
question for the dataset structur

#30 lucafei opened 3 years ago
2
input and target shapes do not match: input [1 x 1], target [1] at /pytorch/aten/src/THCUNN/generic/MSECriterion.cu:15

#29 kevinchow1993 opened 3 years ago
0
Getting some random noise in generated fake images while training after few epochs and not generating quite clear images even after 60 epochs

#28 Vaishnvi closed 4 years ago
0
SOLUTION: IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

#27 pnzr00t opened 4 years ago
3
PatchGAN loss calculated incorrectly (perhaps)

#26 alexander-soare opened 4 years ago
3
about results

#25 YeHuanjie opened 4 years ago
2
Error in pred_fake shape

#24 nisargshah1999 opened 4 years ago
0
Regarding Visdom

#23 nisargshah1999 opened 4 years ago
2
How can I train the network with the weight file which is output of last train?

#22 wallcuber opened 4 years ago
0
RuntimeError: output with shape [1, 256, 256] doesn't match the broadcast shape [3, 256, 256]

#21 youngjaeshin closed 3 years ago
10
logger = Logger(opt.n_epochs,len(dataloader))为什么它总是报SyntaxError: invalid syntax错误

#20 huangqi111 opened 4 years ago
0
Deprecation removed

#19 kpriyanshu256 opened 4 years ago
0
The expanded size of the tensor must match the existing size at non-singleton dimension 0

#18 latlio opened 4 years ago
4
How does ReplayBuffer behave?

#17 zhangluustb opened 4 years ago
1
Reason for multiplication and addition after generating outputs

#16 patrick-han closed 5 years ago
1
UserWarning: using a target size (torch.Size([1])) that is different to input size (torch.Size([1],[1]))

#15 giuliasilvestro closed 5 years ago
4
Model

#14 ghost opened 5 years ago
0
could you please share your type of GPU, mine always out of memory(4 GIB)

#13 WatchDogesxxx opened 5 years ago
2
Adversarial Loss not trained against stagnant partner?

#12 yhu9 opened 5 years ago
1
needs update utils.py by updating PyTorch0.4

#11 takeru1205 opened 5 years ago
1
why discriminator is designed like this?

#10 YunLord opened 5 years ago
1
Training did not converge

#9 Lmy0217 opened 5 years ago
2
Discriminator Activation

#8 sachinruk opened 5 years ago
1
How to use multiple GPUs to train cycleGAN ?

#7 MrLinNing opened 5 years ago
2
Reason for copying the tensors from the dataloader to input tensors

#6 sshkhr opened 5 years ago
2
trivial fix

#5 yudai09 closed 5 years ago
1
Minor fixes

#4 tanvach opened 6 years ago
1
Import Error!

#3 happsky opened 6 years ago
2
Is the comment for Down sampling and Up sampling switched in the Generator Class?

#2 inkplay opened 6 years ago
2
How did you implement PatchGAN??

#1 kenoharada opened 6 years ago
3