Akanimax

@mounaTay yes I am able to start the quepy app. Could you please send the complete stack trace of the error you obtained, we will be better able to debug...

@mounaTay I think I had the same problem too (If I remember correctly, but it was quite similar to this). The way I solved it was by creating a virtualEnv...

@mounaTay well, that's a bit odd. But, I am glad that solved your problem. cheers!

I have been looking for a natural language to sql converter and quepy is the closest what I could find. I am actually planning to generate some synthetic data for...

Hi @LexSong, You are right about the `dataloader` always returning first element of the iterator. But since the dataloader while creation has set `shuffle=True`, It will return different data-points (well,...

@LexSong, Yes, I know it is inefficient. BTW, I am not the author of this code, was just helping. Did you check out the links?

@JoeGardner000, Thanks for the clear issue report. I am only using the opencv for writing the video in the script [pro_gan_pytorch_scripts/latent_space_interpolation.py](https://github.com/akanimax/pro_gan_pytorch/blob/master/pro_gan_pytorch_scripts/latent_space_interpolation.py), so it won't be cumbersome to get rid of...

@MeteoRex11, I see. The latest pro_gan_pytorch package has the projection variant of the conditional ProGAN. Could you try some of the previous versions of the package [here](https://pypi.org/project/pro-gan-pth/#history)? Best regards, @akanimax

Well, there are some known issues regarding the multi-gpu training since the last couple of updates of PyTorch. I will have to investigate this, but it's quite difficult given my...

@mdraw, Thanks a lot for the PR. I'll review it in a couple of days. Thanks again! Best regards, @akanimax