Eduardo Pacheco

> Thanks for your work! I found an issue where the same model produces different results. Take the image of '000000039769.jpg' as an example. The results of the official code...

> it's possible to train? In theory, you can, it wasn't extensively tested, but if you find any problems open an issue in the [transformers](https://github.com/huggingface/transformers) repo and tag me there

Hello there, is this issue resolved? @tsabbir96 are you still working on it? Otherwise I would love to give it a try

Hey @mariosasko, I've taken the time to take a look at how we load the datasets usually. My main question now is about the final solution. So the idea is...

> Is this issue still open? If yes, I'd like to work upon on it. Thanks Definitely still open. I gave it a try, but then didn't get any feedback...

@NielsRogge just pinging you here

Hey @NielsRogge, could you take a look at the PR? Code quality is failing, but is unrelated and the documentation tests I don't know what is going on because it's...

> Looks like we're nearly there. Just one comment, could we make the current `post_process_masks` method consistent with the existing `post_process_semantic_segmentation` and `post_process_instance_segmentation` methods in the library (perhaps also leveraging...

> Awesome work! Thanks for all the work adding and iterating on this > > Just some tiny nits. Please do not just mark comments as resolved when they are...

> @EduardoPach The checkpoints should be uploaded under the correct org - @NielsRogge can help you with that. Then all the checkpoint references in this PR need to be updated...