Alexander Tong

Hi, I just ran into this issue on our compute cluster with local python environments. I have tried the above branch and it solves my issue.

Hi Michal, PHATE embedding is not necessary for either Meld or VFC. You can just substitute data_phate for any embedding and this should work fine. One caveat, MELD and VFC,...

Check here for my latest (public) uses * https://github.com/atong01/conditional-flow-matching * https://github.com/atong01/trainable_symmetry * https://github.com/lazaratan/dyn-gfn Happy to start a dedicated thread, but off the top of my head the most interesting areas...

@radiradev Thats a great idea. I can work on this. If you have an immediate need or are interested in making one I can send over a dirty notebook for...

I would implement this by inheriting from the SuperResModel class i.e. ``` class MySuperResModel(SuperResModel): def forward(t, x): return super().forward(t, x, model_kwargs) ``` I think we do this in the conditional...

I believe the basic torchcfm codebase plays fairly nicely with torch 2.0, but the code in `runner` reproducing things from the papers does not. Specifically even the versions of `pytorch_lightning`...

If you are trying to calculate the EMD between diracs (treating each point as a separate distribution), then you would want `labels = np.eye(npts)`. In general `labels` should be a...

It appears this under corrects this data and should be further investigated.

Hi, thanks for your interest and sorry for not getting back sooner. I would mention that because of the model architecture it trains almost as fast on a good CPU...

Hi Shushant, when things work correctly there should be a mp4 along with those jpegs. The code that does this is in `TrajectoryNet/lib/viz_scrna.py`. it works by producing a bunch of...