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>
This commit is contained in:
Sayak Paul
2022-06-08 18:33:18 +05:30
committed by GitHub
parent 78c695eb62
commit 9d99489f2f
10 changed files with 590 additions and 6 deletions

View File

@@ -42,7 +42,7 @@ Tips:
This model was contributed by [edugp](https://huggingface.co/edugp) and [patrickvonplaten](https://huggingface.co/patrickvonplaten).
[sayakpaul](https://github.com/sayakpaul) contributed Data2Vec for vision in TensorFlow.
[sayakpaul](https://github.com/sayakpaul) and [Rocketknight1](https://github.com/Rocketknight1) contributed Data2Vec for vision in TensorFlow.
The original code (for NLP and Speech) can be found [here](https://github.com/pytorch/fairseq/tree/main/examples/data2vec).
The original code for vision can be found [here](https://github.com/facebookresearch/data2vec_vision/tree/main/beit).
@@ -145,3 +145,8 @@ The original code for vision can be found [here](https://github.com/facebookrese
[[autodoc]] TFData2VecVisionForImageClassification
- call
## TFData2VecVisionForSemanticSegmentation
[[autodoc]] TFData2VecVisionForSemanticSegmentation
- call