msseibel

I also had a hard time installing this. I am using python 3.8 and a conda environment. Here is what helped me: Add `# cython: language_level=3` to soft_dtw_fast.pyx run: cd...

Thank you. This is great. The [UMAP project](https://github.com/lmcinnes/umap/issues/310) was in need of a differentiable implementation of DTW. I am going to link the numba version, since the UMAP implementation is...

Ran in the same problem and I am writing this comment just to remind the author (after one year) to react on this. A repository with 530 stars should be...

As a short warning: Trying to build an image with privileged rights (as it is necessary for the `umount`) will bring you down a rabbit hole. Good luck: https://stackoverflow.com/questions/48098671/build-with-docker-and-privileged I...

Did you try to use the StyleGAN Generator? That should allow you to specify a latent vector for controlling the translated image. I am also very much interested in seeing...

Just found a paper that uses an approach similar to CUT and combines it with neural style transfer: Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning, Zhang et al....

Hi @MariyaLapaeva and @danivelikova, have you been able to use the wgangp version? I am also working with medical data and lsgan runs into some kind of mode collapse.

When I try to run the image example I run into the same problem but with 50.71GiB. It seems to be independent of the batchsize?!

Just in case someone else stumples about this: There exists a more recent version directly in the pytorch geometric repository under torch_geometric/nn/conv.