Nicolas Hug

Hi @rizavelioglu Supporting encoded RLE masks sounds reasonable, but before we proceed, can you show me how you would like to define and wrap your custom dataset? Does it directly...

Thank you @rizavelioglu - I have opened https://github.com/pytorch/vision/pull/8387 to support encoded RLE segmentation. Do you mind taking a look at the PR and confirm that this is indeed what you...

Thanks for the feature request @matlabninja . Supporting 1. and 3. SGTM, we could add `target_types="binary-category"` and `target_types="detection"`. I'm not sure I completely follow what you mean by 2. though...

Sorry folks, I would have to double check but what's probably happening is that we fixed the compilation issue on `main` but did not cherry-pick it onto the release branche(s).

Thanks for the PR @NSalberg , I followed-up and made the requested changes in https://github.com/pytorch/vision/pull/8452

Thanks for the feature request @sidijju . In order to get `[500, 250]` and `[250, 500]` from these specific input images, you could set `size=499, max_size=500`. But of course, this...

Thanks for your feedback @sidijju . I'm happy to review a PR from you if you'd like to try to submit one. Our contributing guide is here: https://github.com/pytorch/vision/blob/main/CONTRIBUTING.md For this...

Hi @sidijju , We'll have to make sure the v2 version is still compatible with v1. However, there should be an easy workaround for the issue you're seeing - e.g....

Closed by https://github.com/pytorch/vision/pull/8459, thank you @sidijju ! Thanks for the feedback @MyNameIsFu , this will be available soon in the next version (0.19)

Hi @Tomsen1410 , thanks for the report. Compiling `resize_image()` should work in general although there might be edge cases with the bicubic mode. Can you share the details of the...