aitorzip/PyTorch-CycleGAN

Issues

• 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 opened a month ago by Chopper525
  0

• picture size

  #43 opened a year ago by trash-boy
  1

• about results

  #25 opened 4 years ago by YeHuanjie
  2

• Regarding Visdom

  #23 opened 4 years ago by nisargshah1999
  2

• Training problems：Setting up a new session

  #34 opened 3 years ago by chenmw269
  1

• Training did not converge

  #9 opened 6 years ago by Lmy0217
  2

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

  #44 opened a year ago by UrielV1
  0

• 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 opened a year ago by guanjingshuo
  0

• Can the results same as the official implement?

  #41 opened 2 years ago by Ssakura-go
  1

• Reason for copying the tensors from the dataloader to input tensors

  #6 opened 6 years ago by sshkhr
  2

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

  #35 opened 3 years ago by chenmw269
  2

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

  #33 opened 3 years ago by JimberZ
  8

• question about train

  #37 opened 3 years ago by xiaofeng-c
  1

• PatchGAN loss calculated incorrectly (perhaps)

  #26 opened 4 years ago by alexander-soare
  3

• about identity loss

  #39 opened 2 years ago by karim-moon
  1

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

  #38 opened 3 years ago by KeatsHao
  0

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

  #18 opened 5 years ago by latlio
  4

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

  #36 opened 3 years ago by yanjinwei143
  0

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

  #27 opened 4 years ago by pnzr00t
  3

• Training did not converge,how to change the parameters?plz!

  #32 opened 3 years ago by Emir-Liu
  1

• question for the dataset structur

  #30 opened 4 years ago by lucafei
  2

• why not fix D while updating G?

  #31 opened 3 years ago by XiaoyuShi97
  1

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

  #21 opened 4 years ago by youngjaeshin
  10

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

  #29 opened 4 years ago by kevinchow1993
  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 opened 4 years ago by Vaishnvi
  0

• How did you implement PatchGAN??

  #1 opened 6 years ago by kenoharada
  3

• Error in pred_fake shape

  #24 opened 4 years ago by nisargshah1999
  0

• How can I train the network with the weight file which is output of last train?

  #22 opened 4 years ago by wallcuber
  0

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

  #20 opened 4 years ago by huangqi111
  0

• Discriminator Activation

  #8 opened 6 years ago by sachinruk
  1

• needs update utils.py by updating PyTorch0.4

  #11 opened 5 years ago by takeru1205
  1

• How does ReplayBuffer behave?

  #17 opened 5 years ago by zhangluustb
  1

• How to use multiple GPUs to train cycleGAN ?

  #7 opened 6 years ago by MrLinNing
  2

• Is the comment for Down sampling and Up sampling switched in the Generator Class?

  #2 opened 6 years ago by inkplay
  2

• Reason for multiplication and addition after generating outputs

  #16 opened 5 years ago by patrick-han
  1

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

  #15 opened 5 years ago by giuliasilvestro
  4

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

  #13 opened 5 years ago by WatchDogesxxx
  2

• Model

  #14 opened 5 years ago
  0

• why discriminator is designed like this?

  #10 opened 5 years ago by YunLord
  1

• Adversarial Loss not trained against stagnant partner?

  #12 opened 5 years ago by yhu9
  1

• Import Error!

  #3 opened 6 years ago by happsky
  2