Conversation
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
2Added Deformable Detr Encoder classes from deformable_detr Implementation for pixel Decoder Fixed Pixel Decoder Implementation
Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
2. Added checkpoint conversion script for mask2former 3. Updated feature extractor for instance segmentation post processing 4. Doc string updates 5. config file fixes
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
src/transformers/models/mask2former/image_processing_mask2former.py
Outdated
Show resolved
Hide resolved
NielsRogge
left a comment
There was a problem hiding this comment.
Thanks a lot for working on this model! 🙏 Left some final comments.
|
So it seems there are 2 todo's left:
|
Sure I'll connect with @alaradirik and we'll fix these shortly and update you. |
|
@NielsRogge Just wanted to update that backbone for Mask2Former has been switched to Conversion of all 30 checkpoints from Mask2Former model zoo using swin backbone corresponding to all 4 datasets and segmentation tasks is done and are available on the Hub. I just need to update the model cards. Will finish that shortly too. |
|
Thank you! I'm just wondering why the issue was occurring only on Swin-base on one specific dataset. It would definitely be nice to clear that up, does it have to do with the image resolution? For instance for UperNet (at #20648) I was able to perfectly convert all checkpoints that leverage Swin-base by using our |
b2520e6 to
5d2de81
Compare
What does this PR do?
Adds Mask2Former to transformers.
Original repo: https://github.com/facebookresearch/Mask2Former/
Paper: https://arxiv.org/abs/2112.01527
Co-authored with @shivalikasingh95
To Do:
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.