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

Refactoring of ImageProcessorFast (#35069)

Browse Source 
* add init and base image processing functions

* add add_fast_image_processor to transformers-cli

* add working fast image processor clip

* add fast image processor to doc, working tests

* remove "to be implemented" SigLip

* fix unprotected import

* fix unprotected vision import

* update ViTImageProcessorFast

* increase threshold slow fast ewuivalence

* add fast img blip

* add fast class in tests with cli

* improve cli

* add fast image processor convnext

* add LlavaPatchingMixin and fast image processor for llava_next and llava_onevision

* add device kwarg to ImagesKwargs for fast processing on cuda

* cleanup

* fix unprotected import

* group images by sizes and add batch processing

* Add batch equivalence tests, skip when center_crop is used

* cleanup

* update init and cli

* fix-copies

* refactor convnext, cleanup base

* fix

* remove patching mixins, add piped torchvision transforms for ViT

* fix unbatched processing

* fix f strings

* protect imports

* change llava onevision to class transforms (test)

* fix convnext

* improve formatting (following Pavel review)

* fix handling device arg

* improve cli

* fix

* fix inits

* Add distinction between preprocess and _preprocess, and support for arbitrary kwargs through valid_extra_kwargs

* uniformize qwen2_vl fast

* fix docstrings

* add add fast image processor llava

* remove min_pixels max_pixels from accepted size

* nit

* nit

* refactor fast image processors docstrings

* cleanup and remove fast class transforms

* update add fast image processor transformers cli

* cleanup docstring

* uniformize pixtral fast and  make _process_image explicit

* fix prepare image structure llava next/onevision

* Use typed kwargs instead of explicit args

* nit fix import Unpack

* clearly separate pops and gets in base preprocess. Use explicit typed kwargs

* make qwen2_vl preprocess arguments hashable
This commit is contained in:
Yoni Gozlan
2025-02-04 17:52:31 -05:00
committed by GitHub
parent 8d73a38606
commit fa56dcc2ab
66 changed files with 4047 additions and 2244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
tests/models/clip/test_image_processing_clip.py
View File

@@ -17,7 +17,7 @@
import unittest
from transformers.testing_utils import require_torch, require_vision
from transformers.utils import is_vision_available
from transformers.utils import is_torchvision_available, is_vision_available
from ...test_image_processing_common import ImageProcessingTestMixin, prepare_image_inputs
@@ -25,6 +25,9 @@ from ...test_image_processing_common import ImageProcessingTestMixin, prepare_im
if is_vision_available():
from transformers import CLIPImageProcessor
if is_torchvision_available():
from transformers import CLIPImageProcessorFast
class CLIPImageProcessingTester:
def __init__(
@@ -44,6 +47,7 @@ class CLIPImageProcessingTester:
image_std=[0.26862954, 0.26130258, 0.27577711],
do_convert_rgb=True,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent
@@ -92,6 +96,7 @@ class CLIPImageProcessingTester:
@require_vision
class CLIPImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
image_processing_class = CLIPImageProcessor if is_vision_available() else None
fast_image_processing_class = CLIPImageProcessorFast if is_torchvision_available() else None
def setUp(self):
super().setUp()
@@ -102,21 +107,23 @@ class CLIPImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
return self.image_processor_tester.prepare_image_processor_dict()
def test_image_processor_properties(self):
image_processing = self.image_processing_class(**self.image_processor_dict)
self.assertTrue(hasattr(image_processing, "do_resize"))
self.assertTrue(hasattr(image_processing, "size"))
self.assertTrue(hasattr(image_processing, "do_center_crop"))
self.assertTrue(hasattr(image_processing, "center_crop"))
self.assertTrue(hasattr(image_processing, "do_normalize"))
self.assertTrue(hasattr(image_processing, "image_mean"))
self.assertTrue(hasattr(image_processing, "image_std"))
self.assertTrue(hasattr(image_processing, "do_convert_rgb"))
for image_processing_class in self.image_processor_list:
image_processing = image_processing_class(**self.image_processor_dict)
self.assertTrue(hasattr(image_processing, "do_resize"))
self.assertTrue(hasattr(image_processing, "size"))
self.assertTrue(hasattr(image_processing, "do_center_crop"))
self.assertTrue(hasattr(image_processing, "center_crop"))
self.assertTrue(hasattr(image_processing, "do_normalize"))
self.assertTrue(hasattr(image_processing, "image_mean"))
self.assertTrue(hasattr(image_processing, "image_std"))
self.assertTrue(hasattr(image_processing, "do_convert_rgb"))
def test_image_processor_from_dict_with_kwargs(self):
image_processor = self.image_processing_class.from_dict(self.image_processor_dict)
self.assertEqual(image_processor.size, {"shortest_edge": 20})
self.assertEqual(image_processor.crop_size, {"height": 18, "width": 18})
for image_processing_class in self.image_processor_list:
image_processor = image_processing_class.from_dict(self.image_processor_dict)
self.assertEqual(image_processor.size, {"shortest_edge": 20})
self.assertEqual(image_processor.crop_size, {"height": 18, "width": 18})
image_processor = self.image_processing_class.from_dict(self.image_processor_dict, size=42, crop_size=84)
self.assertEqual(image_processor.size, {"shortest_edge": 42})
self.assertEqual(image_processor.crop_size, {"height": 84, "width": 84})
image_processor = image_processing_class.from_dict(self.image_processor_dict, size=42, crop_size=84)
self.assertEqual(image_processor.size, {"shortest_edge": 42})
self.assertEqual(image_processor.crop_size, {"height": 84, "width": 84})