transformers/docs/source
Sayak Paul 9d99489f2f
Add TFData2VecVision for semantic segmentation (#17271)
* feat: initial implementation of data2vec segmentation model in TF.

* chore: minor corrections to make the segmenter work.

* chore: removed unncessary files.

* chore: add tests and other modifications.

* fix: loss computation for segmentation.

* chore: remove unused variable.

* chore: formatting.

* added a dummy adaptive pooling layer.

* removed unnecessary file.

* potentially add identifiers to layer names.

* fix: layer naming.

* chore: removed unnecessary print.

* Skipping unneeded test

* chore: add logging to debug tolerance.

* fix: segmentation tests for tfdata2vecvision

* chore: make style.

* fix: layer names, assertion to be resolved.

* Bumping test tolerance a bit

* chore: bump the tol in PT test.

Co-authored-by: matt <rocketknight1@gmail.com>
2022-06-08 14:03:18 +01:00
..
en Add TFData2VecVision for semantic segmentation (#17271) 2022-06-08 14:03:18 +01:00
es Fix gendered sentence in Spanish translation(#17558) 2022-06-07 14:09:39 +02:00
it Translation/italian: added pipeline_tutorial.mdx [Issue: #17459] (#17507) 2022-06-06 10:35:20 -04:00
pt quicktour.mdx en -> pt translation (#17074) 2022-06-07 17:35:05 -04:00
_config.py Use doc builder styler (#16412) 2022-03-28 07:45:18 -04:00