Add CLIPSeg (#20066)

* Add first draft

* Update conversion script

* Improve conversion script

* Improve conversion script some more

* Add conditional embeddings

* Add initial decoder

* Fix activation function of decoder

* Make decoder outputs match original implementation

* Make decoder outputs match original implementation

* Add more copied from statements

* Improve model outputs

* Fix auto tokenizer file

* Fix more tests

* Add test

* Improve README and docs, improve conditional embeddings

* Fix more tests

* Remove print statements

* Remove initial embeddings

* Improve conversion script

* Add interpolation of position embeddings

* Finish addition of interpolation of position embeddings

* Add support for refined checkpoint

* Fix refined checkpoint

* Remove unused parameter

* Improve conversion script

* Add support for training

* Fix conversion script

* Add CLIPSegFeatureExtractor

* Fix processor

* Fix CLIPSegProcessor

* Fix conversion script

* Fix most tests

* Fix equivalence test

* Fix README

* Add model to doc tests

* Use better variable name

* Convert other checkpoint as well

* Update config, add link to paper

* Add docs

* Update organization

* Replace base_model_prefix with clip

* Fix base_model_prefix

* Fix checkpoint of config

* Fix config checkpoint

* Remove file

* Use logits for output

* Fix tests

Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>

utils/check_repo.py

@@ -46,6 +46,7 @@ PRIVATE_MODELS = [
 # Being in this list is an exception and should **not** be the rule.
 IGNORE_NON_TESTED = PRIVATE_MODELS.copy() + [
     # models to ignore for not tested
+    "CLIPSegDecoder",  # Building part of bigger (tested) model.
     "TableTransformerEncoder",  # Building part of bigger (tested) model.
     "TableTransformerDecoder",  # Building part of bigger (tested) model.
     "TimeSeriesTransformerEncoder",  # Building part of bigger (tested) model.
@@ -140,6 +141,9 @@ TEST_FILES_WITH_NO_COMMON_TESTS = [
 # should **not** be the rule.
 IGNORE_NON_AUTO_CONFIGURED = PRIVATE_MODELS.copy() + [
     # models to ignore for model xxx mapping
+    "CLIPSegForImageSegmentation",
+    "CLIPSegVisionModel",
+    "CLIPSegTextModel",
     "EsmForProteinFolding",
     "TimeSeriesTransformerForPrediction",
     "PegasusXEncoder",

utils/documentation_tests.txt

@@ -35,6 +35,7 @@ src/transformers/models/bloom/configuration_bloom.py
 src/transformers/models/camembert/configuration_camembert.py
 src/transformers/models/canine/configuration_canine.py
 src/transformers/models/clip/configuration_clip.py
+src/transformers/models/clipseg/modeling_clipseg.py
 src/transformers/models/codegen/configuration_codegen.py
 src/transformers/models/conditional_detr/configuration_conditional_detr.py
 src/transformers/models/conditional_detr/modeling_conditional_detr.py
@@ -187,4 +188,4 @@ src/transformers/models/xlnet/configuration_xlnet.py
 src/transformers/models/yolos/configuration_yolos.py
 src/transformers/models/yolos/modeling_yolos.py
 src/transformers/models/x_clip/modeling_x_clip.py
-src/transformers/models/yoso/configuration_yoso.py
+src/transformers/models/yoso/configuration_yoso.py