Atharva Sehgal

Also facing this issue while logging images! Happy to provide any logs/code/etc. if needed. Edit: This was a bug in my code. My training/validation/testing split were calling the same visualization...

Hi! Thanks for the update. Just fixed the error after recreating it on a linux box. Sorry about that! ``` (torchvision) asehgal@ubuntu:~/vision$ pytest test/test_ops.py -vvv -k test_masks_box ================================================== test session...

Hi! Here are the results running on a GPU [updated script [here](https://gist.github.com/atharvas/34a9a423027504848f96281f881b4d4c)]. This is an `NVIDIA RTX 2080 Ti`. I increased the max batch size to $2^{15}$. Speed Comparison: ...

Hello! Thanks for the input! I've submitted a PR [here](https://github.com/pytorch/vision/pull/8194#issue-2063406059). @NicolasHug: I'm using `masks_to_boxes` to crop an image based on the output of a mask prediction model as one step...

Sounds good. I'll make the necessary changes and push again. I wasn't impressed with the benchmarking results either so I definitely need to rework this to remove the `@unstable`'s.

Hey sorry for the delay on this. I'm going to restart work in this and hope to have it in a merge-able state end of the week.

@MilesCranmer . Apologies but I don't think I'll have the bandwidth to finish this PR until the end of September (hopefully in time for v2.1, if I can't make v2.0).

closing this in favor of #505

I was encountering some issues with constraint parsing in `Options.jl`. Check out the comment. Don't know why the test cases don't catch the issue.

Gosh. Looking at this now. I was on the wrong branch the whole time.