PyTorch-CycleGAN

PyTorch-CycleGAN copied to clipboard

kpriyanshu256

How does ReplayBuffer behave?

1

w/o ReplayBuffer, is there any data/paper to support ReplayBuffer?

zhangluustb

How to use multiple GPUs to train cycleGAN ?

2

MrLinNing

Reason for copying the tensors from the dataloader to input tensors

2

Hi Aitor. Thanks for the excellent code. I was trying to make some modifications and use CycleGAN for a project of mine. I am often running into memory issues which...

sshkhr

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

2

`In = 64` `out = in*2`

inkplay

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

2

WatchDogesxxx

Could you please share your model? I don`t have a proper GPU.Thanks!

ghost

why discriminator is designed like this?

1

loss_D_real = criterion_GAN(pred_real, torch.ones_like(pred_real));i think this should be loss_D_real = criterion_GAN(pred_real, torch.zeros_like(pred_real))

YunLord

Adversarial Loss not trained against stagnant partner?

1

I was under the impression that the optimizer and the generator should be training against stagnant counterparts but the step function on the generators are called before the gradients are...

yhu9

Training did not converge

2

I got loss as follows ``` ... 2018-10-27 Saturday 02:21:32 : Train Epoch: 1 [213/284 (75%)] loss_G: 13.778452 loss_G_identity: 4.409110 loss_G_GAN: 0.245768 loss_G_cycle: 9.123573 loss_D: 1.171054 2018-10-27 Saturday 02:21:33 :...

Lmy0217