SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add Image Processors (#19796)

Browse Source 
* Add CLIP image processor

* Crop size as dict too

* Update warning

* Actually use logger this time

* Normalize doesn't change dtype of input

* Add perceiver image processor

* Tidy up

* Add DPT image processor

* Add Vilt image processor

* Tidy up

* Add poolformer image processor

* Tidy up

* Add LayoutLM v2 and v3 imsge processors

* Tidy up

* Add Flava image processor

* Tidy up

* Add deit image processor

* Tidy up

* Add ConvNext image processor

* Tidy up

* Add levit image processor

* Add segformer image processor

* Add in post processing

* Fix up

* Add ImageGPT image processor

* Fixup

* Add mobilevit image processor

* Tidy up

* Add postprocessing

* Fixup

* Add VideoMAE image processor

* Tidy up

* Add ImageGPT image processor

* Fixup

* Add ViT image processor

* Tidy up

* Add beit image processor

* Add mobilevit image processor

* Tidy up

* Add postprocessing

* Fixup

* Fix up

* Fix flava and remove tree module

* Fix image classification pipeline failing tests

* Update feature extractor in trainer scripts

* Update pad_if_smaller to accept tuple and int size

* Update for image segmentation pipeline

* Update src/transformers/models/perceiver/image_processing_perceiver.py

Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>

* Update src/transformers/image_processing_utils.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/beit/image_processing_beit.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* PR comments - docstrings; remove accidentally added resize; var names

* Update docstrings

* Add exception if size is not in the right format

* Fix exception check

* Fix up

* Use shortest_edge in tuple in script

Co-authored-by: Alara Dirik <8944735+alaradirik@users.noreply.github.com>
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
This commit is contained in:
amyeroberts
2022-11-02 11:57:36 +00:00
committed by GitHub
parent 2e3452af0f
commit a6b7759880
65 changed files with 7060 additions and 3590 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
tests/models/videomae/test_feature_extraction_videomae.py
View File

@@ -44,11 +44,15 @@ class VideoMAEFeatureExtractionTester(unittest.TestCase):
min_resolution=30,
max_resolution=400,
do_resize=True,
size=18,
size=None,
do_normalize=True,
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
crop_size=None,
):
size = size if size is not None else {"shortest_edge": 18}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels
@@ -61,6 +65,7 @@ class VideoMAEFeatureExtractionTester(unittest.TestCase):
self.do_normalize = do_normalize
self.image_mean = image_mean
self.image_std = image_std
self.crop_size = crop_size
def prepare_feat_extract_dict(self):
return {
@@ -69,6 +74,7 @@ class VideoMAEFeatureExtractionTester(unittest.TestCase):
"do_normalize": self.do_normalize,
"do_resize": self.do_resize,
"size": self.size,
"crop_size": self.crop_size,
}
@@ -91,6 +97,7 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
self.assertTrue(hasattr(feature_extractor, "image_std"))
self.assertTrue(hasattr(feature_extractor, "do_normalize"))
self.assertTrue(hasattr(feature_extractor, "do_resize"))
self.assertTrue(hasattr(feature_extractor, "do_center_crop"))
self.assertTrue(hasattr(feature_extractor, "size"))
def test_batch_feature(self):
@@ -113,8 +120,8 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
1,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)
@@ -126,8 +133,8 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
self.feature_extract_tester.batch_size,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)
@@ -148,8 +155,8 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
1,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)
@@ -161,8 +168,8 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
self.feature_extract_tester.batch_size,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)
@@ -183,8 +190,8 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
1,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)
@@ -196,7 +203,7 @@ class VideoMAEFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.T
self.feature_extract_tester.batch_size,
self.feature_extract_tester.num_frames,
self.feature_extract_tester.num_channels,
self.feature_extract_tester.size,
self.feature_extract_tester.size,
self.feature_extract_tester.crop_size["height"],
self.feature_extract_tester.crop_size["width"],
),
)