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

Add ViTImageProcessorFast to tests (#31424)

Browse Source 
* Add ViTImageProcessor to tests

* Correct data format

* Review comments
This commit is contained in:
amyeroberts
2024-06-25 13:36:58 +01:00
committed by GitHub
parent aab0829790
commit 0f67ba1d74
26 changed files with 230 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

144
tests/models/idefics2/test_image_processing_idefics2.py
View File

@@ -99,6 +99,8 @@ class Idefics2ImageProcessingTester(unittest.TestCase):
image = image_inputs[0]
if isinstance(image, Image.Image):
w, h = image.size
elif isinstance(image, np.ndarray):
h, w = image.shape[0], image.shape[1]
else:
h, w = image.shape[1], image.shape[2]
@@ -176,6 +178,10 @@ class Idefics2ImageProcessingTester(unittest.TestCase):
if torchify:
images_list = [[torch.from_numpy(image) for image in images] for images in images_list]
if numpify:
# Numpy images are typically in channels last format
images_list = [[image.transpose(1, 2, 0) for image in images] for images in images_list]
return images_list
@@ -206,66 +212,100 @@ class Idefics2ImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
self.assertTrue(hasattr(image_processing, "do_image_splitting"))
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=False, numpify=True)
for sample_images in image_inputs:
for image in sample_images:
self.assertIsInstance(image, np.ndarray)
for image_processing_class in self.image_processor_list:
# 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=False, numpify=True)
for sample_images in image_inputs:
for image in sample_images:
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 = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
self.assertEqual(
tuple(encoded_images.shape), (self.image_processor_tester.batch_size, *expected_output_image_shape)
)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
self.assertEqual(
tuple(encoded_images.shape), (self.image_processor_tester.batch_size, *expected_output_image_shape)
)
def test_call_numpy_4_channels(self):
for image_processing_class in self.image_processor_list:
# Initialize image_processing
image_processor_dict = self.image_processor_dict
image_processor_dict["image_mean"] = [0.5, 0.5, 0.5, 0.5]
image_processor_dict["image_std"] = [0.5, 0.5, 0.5, 0.5]
image_processing = self.image_processing_class(**image_processor_dict)
# create random numpy tensors
self.image_processor_tester.num_channels = 4
image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=False, numpify=True)
for sample_images in image_inputs:
for image in sample_images:
self.assertIsInstance(image, np.ndarray)
# Test not batched input
encoded_images = image_processing(
image_inputs[0], input_data_format="channels_last", return_tensors="pt"
).pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test batched
encoded_images = image_processing(
image_inputs, input_data_format="channels_last", return_tensors="pt"
).pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
self.assertEqual(
tuple(encoded_images.shape), (self.image_processor_tester.batch_size, *expected_output_image_shape)
)
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=False)
for images in image_inputs:
for image in images:
self.assertIsInstance(image, Image.Image)
for image_processing_class in self.image_processor_list:
# 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=False)
for images in image_inputs:
for image in images:
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 = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
self.assertEqual(
tuple(encoded_images.shape), (self.image_processor_tester.batch_size, *expected_output_image_shape)
)
# Test batched
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
self.assertEqual(
tuple(encoded_images.shape), (self.image_processor_tester.batch_size, *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=False, torchify=True)
for image_processing_class in self.image_processor_list:
# 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=False, torchify=True)
for images in image_inputs:
for image in images:
self.assertIsInstance(image, torch.Tensor)
for images in image_inputs:
for image in images:
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 = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test not batched input
encoded_images = image_processing(image_inputs[0], return_tensors="pt").pixel_values
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape([image_inputs[0]])
self.assertEqual(tuple(encoded_images.shape), (1, *expected_output_image_shape))
# Test batched
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
self.assertEqual(
tuple(encoded_images.shape),
(self.image_processor_tester.batch_size, *expected_output_image_shape),
)
# Test batched
expected_output_image_shape = self.image_processor_tester.expected_output_image_shape(image_inputs)
encoded_images = image_processing(image_inputs, return_tensors="pt").pixel_values
self.assertEqual(
tuple(encoded_images.shape),
(self.image_processor_tester.batch_size, *expected_output_image_shape),
)