Add Image Processors (#19796)
* 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
@@ -41,12 +41,15 @@ class PoolFormerFeatureExtractionTester(unittest.TestCase):
|
||||
min_resolution=30,
|
||||
max_resolution=400,
|
||||
do_resize_and_center_crop=True,
|
||||
size=30,
|
||||
size=None,
|
||||
crop_pct=0.9,
|
||||
crop_size=None,
|
||||
do_normalize=True,
|
||||
image_mean=[0.5, 0.5, 0.5],
|
||||
image_std=[0.5, 0.5, 0.5],
|
||||
):
|
||||
size = size if size is not None else {"shortest_edge": 30}
|
||||
crop_size = crop_size if crop_size is not None else {"height": 30, "width": 30}
|
||||
self.parent = parent
|
||||
self.batch_size = batch_size
|
||||
self.num_channels = num_channels
|
||||
@@ -55,6 +58,7 @@ class PoolFormerFeatureExtractionTester(unittest.TestCase):
|
||||
self.do_resize_and_center_crop = do_resize_and_center_crop
|
||||
self.size = size
|
||||
self.crop_pct = crop_pct
|
||||
self.crop_size = crop_size
|
||||
self.do_normalize = do_normalize
|
||||
self.image_mean = image_mean
|
||||
self.image_std = image_std
|
||||
@@ -64,6 +68,7 @@ class PoolFormerFeatureExtractionTester(unittest.TestCase):
|
||||
"size": self.size,
|
||||
"do_resize_and_center_crop": self.do_resize_and_center_crop,
|
||||
"crop_pct": self.crop_pct,
|
||||
"crop_size": self.crop_size,
|
||||
"do_normalize": self.do_normalize,
|
||||
"image_mean": self.image_mean,
|
||||
"image_std": self.image_std,
|
||||
@@ -111,8 +116,8 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
1,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
@@ -123,8 +128,8 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
self.feature_extract_tester.batch_size,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
@@ -143,8 +148,8 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
1,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
@@ -155,8 +160,8 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
self.feature_extract_tester.batch_size,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
@@ -175,8 +180,8 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
1,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
@@ -187,7 +192,7 @@ class PoolFormerFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest
|
||||
(
|
||||
self.feature_extract_tester.batch_size,
|
||||
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"],
|
||||
),
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user