aitorzip/PyTorch-CycleGAN issues and pull requests

#45 - 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

Issue - State: open - Opened by Chopper525 7 months ago - 1 comment

#44 - Beginners' question: Is there a way to use a pre-trained model, or that I have to train it myself?

Issue - State: open - Opened by UrielV1 over 1 year ago

#43 - picture size

Issue - State: open - Opened by trash-boy over 1 year ago - 1 comment

#42 - 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.

Issue - State: open - Opened by guanjingshuo over 1 year ago

#41 - Can the results same as the official implement?

Issue - State: open - Opened by Ssakura-go about 2 years ago - 1 comment

#40 - New: modernized repository

Pull Request - State: open - Opened by arnauddhaene over 2 years ago

#39 - about identity loss

Issue - State: closed - Opened by karim-moon almost 3 years ago - 1 comment

#38 - Pls tell me why derive the discriminator loss function w.r.t. the label rather than the input data.

Issue - State: open - Opened by KeatsHao about 3 years ago

#37 - question about train

Issue - State: open - Opened by xiaofeng-c over 3 years ago - 1 comment

#36 - RuntimeError: The expanded size of the tensor (1224) must match the existing size (370) at non-singleton dimension 2

Issue - State: open - Opened by yanjinwei143 over 3 years ago

#35 - RuntimeError: The expanded size of the tensor (1) must match the existing size (3) at non-singleton dimension 0

Issue - State: open - Opened by chenmw269 over 3 years ago - 2 comments

#34 - Training problems：Setting up a new session

Issue - State: closed - Opened by chenmw269 over 3 years ago - 2 comments

#33 - UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum.

Issue - State: open - Opened by JimberZ over 3 years ago - 8 comments

#32 - Training did not converge,how to change the parameters?plz!

Issue - State: open - Opened by Emir-Liu over 3 years ago - 1 comment

#31 - why not fix D while updating G?

Issue - State: closed - Opened by XiaoyuShi97 almost 4 years ago - 1 comment

#30 - question for the dataset structur

Issue - State: open - Opened by lucafei almost 4 years ago - 2 comments

#29 - input and target shapes do not match: input [1 x 1], target [1] at /pytorch/aten/src/THCUNN/generic/MSECriterion.cu:15

Issue - State: open - Opened by kevinchow1993 over 4 years ago

#28 - Getting some random noise in generated fake images while training after few epochs and not generating quite clear images even after 60 epochs

Issue - State: closed - Opened by Vaishnvi over 4 years ago

#27 - SOLUTION: IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Issue - State: open - Opened by pnzr00t over 4 years ago - 3 comments

#26 - PatchGAN loss calculated incorrectly (perhaps)

Issue - State: open - Opened by alexander-soare over 4 years ago - 3 comments

#25 - about results

Issue - State: open - Opened by YeHuanjie over 4 years ago - 2 comments

#24 - Error in pred_fake shape

Issue - State: open - Opened by nisargshah1999 over 4 years ago

#23 - Regarding Visdom

Issue - State: open - Opened by nisargshah1999 over 4 years ago - 2 comments

#22 - How can I train the network with the weight file which is output of last train?

Issue - State: open - Opened by wallcuber over 4 years ago

#21 - RuntimeError: output with shape [1, 256, 256] doesn't match the broadcast shape [3, 256, 256]

Issue - State: closed - Opened by youngjaeshin almost 5 years ago - 10 comments

#20 - logger = Logger(opt.n_epochs,len(dataloader))为什么它总是报SyntaxError: invalid syntax错误

Issue - State: open - Opened by huangqi111 almost 5 years ago

#19 - Deprecation removed

Pull Request - State: open - Opened by kpriyanshu256 over 5 years ago

#18 - The expanded size of the tensor must match the existing size at non-singleton dimension 0

Issue - State: open - Opened by latlio over 5 years ago - 4 comments

#17 - How does ReplayBuffer behave?

Issue - State: open - Opened by zhangluustb over 5 years ago - 1 comment

#16 - Reason for multiplication and addition after generating outputs

Issue - State: closed - Opened by patrick-han over 5 years ago - 1 comment

#15 - UserWarning: using a target size (torch.Size([1])) that is different to input size (torch.Size([1],[1]))

Issue - State: closed - Opened by giuliasilvestro over 5 years ago - 4 comments

#14 - Model

Issue - State: open - Opened by ghost over 5 years ago

#13 - could you please share your type of GPU, mine always out of memory(4 GIB)

Issue - State: open - Opened by WatchDogesxxx over 5 years ago - 2 comments

#12 - Adversarial Loss not trained against stagnant partner?

Issue - State: open - Opened by yhu9 over 5 years ago - 1 comment

#11 - needs update utils.py by updating PyTorch0.4

Issue - State: open - Opened by takeru1205 almost 6 years ago - 1 comment

#10 - why discriminator is designed like this?

Issue - State: open - Opened by YunLord almost 6 years ago - 1 comment

#9 - Training did not converge

Issue - State: open - Opened by Lmy0217 about 6 years ago - 2 comments

#8 - Discriminator Activation

Issue - State: open - Opened by sachinruk about 6 years ago - 1 comment

#7 - How to use multiple GPUs to train cycleGAN ?

Issue - State: open - Opened by MrLinNing about 6 years ago - 2 comments

#6 - Reason for copying the tensors from the dataloader to input tensors

Issue - State: open - Opened by sshkhr over 6 years ago - 2 comments

#5 - trivial fix

Pull Request - State: closed - Opened by yudai09 over 6 years ago - 1 comment

#4 - Minor fixes

Pull Request - State: open - Opened by tanvach over 6 years ago - 1 comment

#3 - Import Error!

Issue - State: open - Opened by happsky over 6 years ago - 2 comments

#2 - Is the comment for Down sampling and Up sampling switched in the Generator Class?

Issue - State: open - Opened by inkplay over 6 years ago - 2 comments

#1 - How did you implement PatchGAN??

Issue - State: open - Opened by kenoharada almost 7 years ago - 3 comments

GitHub / aitorzip/PyTorch-CycleGAN issues and pull requests