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

Add Fast Image Processor for Chameleon (#37140)

Browse Source 
* Add Fast Image Processor for Chameleon

* add warning to resize and move blend_rgba to convert_to_rgb

* Remove unrelated files

* Update image_processing_chameleon_fast to use auto_docstring

* fix equivalence test

---------

Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
Co-authored-by: yonigozlan <yoni.gozlan@huggingface.co>
This commit is contained in:
farrosalferro
2025-06-28 00:26:57 +09:00
committed by GitHub
parent 6d773fc3bc
commit dd7dc4a4a2
5 changed files with 216 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

156
tests/models/chameleon/test_image_processing_chameleon.py
View File

@@ -16,8 +16,9 @@ import unittest
import numpy as np
from transformers.image_utils import PILImageResampling
from transformers.testing_utils import require_torch, require_vision
from transformers.utils import is_torch_available, is_vision_available
from transformers.utils import is_torch_available, is_torchvision_available, is_vision_available
from ...test_image_processing_common import ImageProcessingTestMixin, prepare_image_inputs
@@ -30,6 +31,9 @@ if is_vision_available():
from transformers import ChameleonImageProcessor
if is_torchvision_available():
from transformers import ChameleonImageProcessorFast
class ChameleonImageProcessingTester:
def __init__(
@@ -48,6 +52,7 @@ class ChameleonImageProcessingTester:
image_mean=[1.0, 1.0, 1.0],
image_std=[1.0, 1.0, 1.0],
do_convert_rgb=True,
resample=PILImageResampling.BILINEAR,
):
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}
@@ -65,6 +70,7 @@ class ChameleonImageProcessingTester:
self.image_mean = image_mean
self.image_std = image_std
self.do_convert_rgb = do_convert_rgb
self.resample = resample
def prepare_image_processor_dict(self):
return {
@@ -76,6 +82,7 @@ class ChameleonImageProcessingTester:
"image_mean": self.image_mean,
"image_std": self.image_std,
"do_convert_rgb": self.do_convert_rgb,
"resample": self.resample,
}
# Copied from tests.models.clip.test_image_processing_clip.CLIPImageProcessingTester.expected_output_image_shape
@@ -99,6 +106,7 @@ class ChameleonImageProcessingTester:
@require_vision
class ChameleonImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
image_processing_class = ChameleonImageProcessor if is_vision_available() else None
fast_image_processing_class = ChameleonImageProcessorFast if is_torchvision_available() else None
# Copied from tests.models.clip.test_image_processing_clip.CLIPImageProcessingTest.setUp with CLIP->Chameleon
def setUp(self):
@@ -111,94 +119,100 @@ class ChameleonImageProcessingTest(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": 18})
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": 18})
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})
def test_call_pil(self):
# Initialize image_processing
image_processing = self.image_processing_class(**self.image_processor_dict)
# create random PIL images
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True)
for image in image_inputs:
self.assertIsInstance(image, Image.Image)
for image_processing_class in self.image_processor_list:
# Initialize image_processing
image_processing = image_processing_class(**self.image_processor_dict)
# create random PIL images
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True)
for image in image_inputs:
self.assertIsInstance(image, Image.Image)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
def test_call_numpy(self):
# Initialize image_processing
image_processing = self.image_processing_class(**self.image_processor_dict)
# create random numpy tensors
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True, numpify=True)
for image in image_inputs:
self.assertIsInstance(image, np.ndarray)
for image_processing_class in self.image_processor_list:
# Initialize image_processing
image_processing = image_processing_class(**self.image_processor_dict)
# create random numpy tensors
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True, numpify=True)
for image in image_inputs:
self.assertIsInstance(image, np.ndarray)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
def test_call_pytorch(self):
# Initialize image_processing
image_processing = self.image_processing_class(**self.image_processor_dict)
# create random PyTorch tensors
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True, torchify=True)
for image_processing_class in self.image_processor_list:
# Initialize image_processing
image_processing = image_processing_class(**self.image_processor_dict)
# create random PyTorch tensors
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True, torchify=True)
for image in image_inputs:
self.assertIsInstance(image, torch.Tensor)
for image in image_inputs:
self.assertIsInstance(image, torch.Tensor)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = (1, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
def test_nested_input(self):
image_processing = self.image_processing_class(**self.image_processor_dict)
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True)
for image_processing_class in self.image_processor_list:
image_processing = image_processing_class(**self.image_processor_dict)
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=True)
# Test batched as a list of images
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched as a list of images
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images.shape), expected_output_image_shape)
# Test batched as a nested list of images, where each sublist is one batch
image_inputs_nested = [image_inputs[:3], image_inputs[3:]]
encoded_images_nested = image_processing(image_inputs_nested, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images_nested.shape), expected_output_image_shape)
# Test batched as a nested list of images, where each sublist is one batch
image_inputs_nested = [image_inputs[:3], image_inputs[3:]]
encoded_images_nested = image_processing(image_inputs_nested, return_tensors="pt").pixel_values
expected_output_image_shape = (7, 3, 18, 18)
self.assertEqual(tuple(encoded_images_nested.shape), expected_output_image_shape)
# Image processor should return same pixel values, independently of input format
self.assertTrue((encoded_images_nested == encoded_images).all())
# Image processor should return same pixel values, independently of input format
self.assertTrue((encoded_images_nested == encoded_images).all())