Jianyi Wang

The same problem on Ubuntu using pip install mmgen. There should be some bugs in the init file.

Similar results after 145k on cifar. I wonder if it is harder to be trained than GAN or it is not stable enough yet...

> @IceClear Do you mind sharing sample images if you could? Sure, here it is (sample 186) after 186k. 

Actually, I think just set drop_last=True for the dataloader in https://github.com/aitorzip/PyTorch-CycleGAN/blob/master/train#L87 solves the bug.

You need to rewrite your dataloader for your own data. Generally, the definition of the dataloaders are [here](https://github.com/xinntao/BasicSR/tree/master/basicsr/data) and you need to write your dataloader in one file follow the...

@fbcotter Thanks for the wonderful code. Actually, I am also trying to use SWT, but the result seems strange in rgb channel.  So is there any plan to finish...

https://colab.research.google.com/github/CompVis/taming-transformers/blob/master/scripts/taming-transformers.ipynb#scrollTo=5rVRrUOwbEH0

@GioFic95 Hi~ Have you finally figured out where is ldm.data.openimages.SuperresOpenImagesAdvancedTrain/Validation and how to train on other datasets? I read the code pipeline and found it a little bit complicated to...

> > @GioFic95 refer to [this line](https://github.com/CompVis/latent-diffusion/blob/main/models/ldm/bsr_sr/config.yaml#L56). second_stage_model of SR ddpm has no encode function, therefore cond_stage_key image is still in **Image Space** not **Latent Space**. Hence this line `...

@lukun199 Hi, have you figured that out? I am also curious about this part of code.