junyanz / BicycleGAN

Toward Multimodal Image-to-Image Translation

https://junyanz.github.io/BicycleGAN/

junyanz/BicycleGAN Issues

Very Large Images
Updated 7 months ago
Hi, please help me.
Updated 10 months ago
Why does not large batch size like 128, 256 work well?
Updated a year ago
Regarding Latent Space Interpolation
Updated 2 years ago
TypeError: __init__() got an unexpected keyword argument 'nl_layer'
Updated 2 years ago
diversity question
Updated 2 years ago
Regarding Training your Own Images
Updated 2 years ago4
Is there <pix2pix+noise> model code that can be directly run？
Closed 2 years ago1
How to train on large images?
Updated 3 years ago
Not clear in the difference between the two latent spaces predicted
Updated 3 years ago5
Incorrect discriminator update for opt.use_same_D
Closed 3 years ago1
Question: Do you need two separate discriminators?
Updated 3 years ago2
Question about generating fake_B_random
Updated 4 years ago
Question about Encoder in cLR-GAN
Updated 4 years ago1
Metric reporting
Updated 4 years ago1
Learn diversity
Closed 5 years ago9
test_before_push is a great rapid test file, but seems outdated?
Updated 4 years ago3
Compute graph wrong and one question
Updated 4 years ago4
Test on single images
Closed 4 years ago1
Question about conditional_D implementation
Closed 4 years ago3
Why my LPIPS distance is larger than what your paper say?
Updated 4 years ago3
Question about PatchGAN perception field
Closed 4 years ago4
Why we use 'retain_graph' when backwarding loss_G?
Closed 4 years ago2
Apply BicycleGAN to improve poor line arts
Updated 4 years ago2
BicycleGAN on Citycscapes
Closed 5 years ago4
different image size not supported.
Closed 4 years ago1
train_night2day.sh problem
Updated 5 years ago1
night2day problems
Updated 5 years ago
Distribution of latent code Z
Closed 5 years ago3
question about the evaluation metrics of diversity
Closed 5 years ago2
Ambiguous about one-to-many
Closed 5 years ago4
Multi-gpu support---only can run on gpu 0
Updated 5 years ago2
D_NLayersMulti implementation correctness
Closed 5 years ago1
Using z as an extra label
Closed 5 years ago2
Why cLR-GAN cause a 15% same results?
Closed 5 years ago2
A little question for latent code z.
Closed 5 years ago2
Expected training time
Closed 5 years ago3
about fake_B_random
Closed 5 years ago4
When to use drop out?
Closed 5 years ago2
Why not freeze netD2
Closed 5 years ago2
ACB import error
Closed 5 years ago1
The result was not very good.
Closed 5 years ago2
Whether it is right about KL_loss
Updated 5 years ago1
No such file or directory
Closed 5 years ago3
About EOFError: Ran out of input
Closed 5 years ago4
not sure if the code is written deliberately about the loss
Closed 5 years ago
what is this means?
Closed 5 years ago5
An Error in train or test `RuntimeError: output with shape [1, 256, 256] doesn't match the broadcast shape [3, 256, 256]`
Closed 5 years ago13
Hi folks, could you try the latest commit? Hopefully, it can address your issues.
Closed 5 years ago
An error in `UnetBlock_with_z`
Closed 5 years ago1