Apoorv Khandelwal

Just circling back, works on my end -- thanks again!

Not certain, but this may be related to #22885.

Thank you very much! Will try this and update you. edit: I'm running into CUDA compatibility issues with `torch==1.12.1` and the CUDA version specific to my system. Might just wait...

Following your conversation, seems like this will not be merged into torch 2.0.1, but is now part of main and will be part of the following release. https://github.com/pytorch/pytorch/pull/97843#issuecomment-1512228321

I believe this issue should still be open, still waiting for the next Pytorch release.

Big +1! I also noticed significant unexpected behavior (i.e. unwanted code being executed) when using Tango. This explains it. Thanks @jmerullo! Imo, all built-in implementations (LocalWorkspace, etc) should be registered...

Thanks for the discussion! Maybe it is simplest to add the following to your `pyproject.toml`? ```toml [project.optional-dependencies] server = ["tornado>=6.2", ] # ... # OR tornado = ["tornado>=6.2"] ``` Then,...

Hi @huangsiyong, thanks for bringing this up. We did actually make some small changes to the dataset between our last post to arxiv and publication. Apologies for the delay in...

I think we can defer to the published ECCV paper, with updated numbers, instead: https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680141.pdf And I've updated the link in this repo's readme.

+1 that would be really great, thank you!