Hans Brouwer

I think the problem might be that you aren't modeling any randomness in the output at all. Your input for a given prompt is deterministic (based on what CLIP says...

This doesn't work for me. When torch is not installed, even when not building the extensions, the line `cmdclass={'build_ext': BuildExtension},` at the end of setup() throws a `NameError: name 'BuildExtension'...

https://github.com/voletiv/mcvd-pytorch Another one!

I've noticed the same thing in my own training runs as well. My first instinct was that it's related to mirroring the dataset, but it looks like you have that...

> I had faced a similar issue. I guess it could be because of the augmentations that you are using. In your config file, you have bgc as the aug_pipe...

Thanks for the in-depth response @universome ! I'll definitely have a look at some of your suggestions. It seems to me maybe it also makes sense to supply the w-code...

~I think this is kind of a fundamental problem with CLIP. CLIP scores images with the exact text significantly higher than images of what the text describes. Using a better...

Yes I want to warmstart with the pretrained checkpoint. Although I get the same error when training from scratch with the crepe embedding loss added in ae.gin. My original training...

Update: I've found that running with only a single GPU (via CUDA_VISIBLE_DEVICES=0) does work to train with the PretrainedCREPEEmbeddingLoss. Is there a way to allow the PretrainedCREPEEmbeddingLoss to work with...

Hey @ruiguo-bio, I believe this is an issue with the "instruments" setting. The list of lists should be made square with the instruments in the corners you want them in....