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

Add Image Processor Fast Deformable DETR (#34353)

Browse Source 
* add deformable detr image processor fast

* add fast processor to doc

* fix copies

* nit docstring

* Add tests gpu/cpu and fix docstrings

* fix docstring

* import changes from detr

* fix imports

* rebase and fix

* fix input data format change in detr and rtdetr fast
This commit is contained in:
Yoni Gozlan
2024-11-19 11:18:58 -05:00
committed by GitHub
parent b99ca4d28b
commit eedc113914
10 changed files with 1427 additions and 212 deletions
Download Patch File Download Diff File Expand all files Collapse all files

167
tests/models/grounding_dino/test_image_processing_grounding_dino.py
View File

@@ -159,26 +159,28 @@ class GroundingDinoImageProcessingTest(AnnotationFormatTestMixin, ImageProcessin
# Copied from tests.models.deformable_detr.test_image_processing_deformable_detr.DeformableDetrImageProcessingTest.test_image_processor_properties with DeformableDetr->GroundingDino
def test_image_processor_properties(self):
image_processing = self.image_processing_class(**self.image_processor_dict)
self.assertTrue(hasattr(image_processing, "image_mean"))
self.assertTrue(hasattr(image_processing, "image_std"))
self.assertTrue(hasattr(image_processing, "do_normalize"))
self.assertTrue(hasattr(image_processing, "do_resize"))
self.assertTrue(hasattr(image_processing, "do_rescale"))
self.assertTrue(hasattr(image_processing, "do_pad"))
self.assertTrue(hasattr(image_processing, "size"))
for image_processing_class in self.image_processor_list:
image_processing = image_processing_class(**self.image_processor_dict)
self.assertTrue(hasattr(image_processing, "image_mean"))
self.assertTrue(hasattr(image_processing, "image_std"))
self.assertTrue(hasattr(image_processing, "do_normalize"))
self.assertTrue(hasattr(image_processing, "do_resize"))
self.assertTrue(hasattr(image_processing, "do_rescale"))
self.assertTrue(hasattr(image_processing, "do_pad"))
self.assertTrue(hasattr(image_processing, "size"))
# Copied from tests.models.deformable_detr.test_image_processing_deformable_detr.DeformableDetrImageProcessingTest.test_image_processor_from_dict_with_kwargs with DeformableDetr->GroundingDino
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, "longest_edge": 1333})
self.assertEqual(image_processor.do_pad, True)
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, "longest_edge": 1333})
self.assertEqual(image_processor.do_pad, True)
image_processor = self.image_processing_class.from_dict(
self.image_processor_dict, size=42, max_size=84, pad_and_return_pixel_mask=False
)
self.assertEqual(image_processor.size, {"shortest_edge": 42, "longest_edge": 84})
self.assertEqual(image_processor.do_pad, False)
image_processor = image_processing_class.from_dict(
self.image_processor_dict, size=42, max_size=84, pad_and_return_pixel_mask=False
)
self.assertEqual(image_processor.size, {"shortest_edge": 42, "longest_edge": 84})
self.assertEqual(image_processor.do_pad, False)
def test_post_process_object_detection(self):
image_processor = self.image_processing_class(**self.image_processor_dict)
@@ -206,40 +208,41 @@ class GroundingDinoImageProcessingTest(AnnotationFormatTestMixin, ImageProcessin
target = {"image_id": 39769, "annotations": target}
# encode them
image_processing = GroundingDinoImageProcessor()
encoding = image_processing(images=image, annotations=target, return_tensors="pt")
for image_processing_class in self.image_processor_list:
# encode them
image_processing = image_processing_class()
encoding = image_processing(images=image, annotations=target, return_tensors="pt")
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1066])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1066])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
# verify area
expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
# verify boxes
expected_boxes_shape = torch.Size([6, 4])
self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
expected_boxes_slice = torch.tensor([0.5503, 0.2765, 0.0604, 0.2215])
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
# verify image_id
expected_image_id = torch.tensor([39769])
self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
# verify class_labels
expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
# verify size
expected_size = torch.tensor([800, 1066])
self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
# verify area
expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
# verify boxes
expected_boxes_shape = torch.Size([6, 4])
self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
expected_boxes_slice = torch.tensor([0.5503, 0.2765, 0.0604, 0.2215])
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
# verify image_id
expected_image_id = torch.tensor([39769])
self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
# verify class_labels
expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
# verify size
expected_size = torch.tensor([800, 1066])
self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
@slow
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_detection_annotations with Detr->GroundingDino
@@ -373,43 +376,45 @@ class GroundingDinoImageProcessingTest(AnnotationFormatTestMixin, ImageProcessin
masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
# encode them
image_processing = GroundingDinoImageProcessor(format="coco_panoptic")
encoding = image_processing(images=image, annotations=target, masks_path=masks_path, return_tensors="pt")
for image_processing_class in self.image_processor_list:
# encode them
image_processing = image_processing_class(format="coco_panoptic")
encoding = image_processing(images=image, annotations=target, masks_path=masks_path, return_tensors="pt")
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1066])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1066])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
# verify area
expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
# verify boxes
expected_boxes_shape = torch.Size([6, 4])
self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
expected_boxes_slice = torch.tensor([0.2625, 0.5437, 0.4688, 0.8625])
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
# verify image_id
expected_image_id = torch.tensor([39769])
self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
# verify class_labels
expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
# verify masks
expected_masks_sum = 822873
self.assertEqual(encoding["labels"][0]["masks"].sum().item(), expected_masks_sum)
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
# verify size
expected_size = torch.tensor([800, 1066])
self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
# verify area
expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
# verify boxes
expected_boxes_shape = torch.Size([6, 4])
self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
expected_boxes_slice = torch.tensor([0.2625, 0.5437, 0.4688, 0.8625])
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
# verify image_id
expected_image_id = torch.tensor([39769])
self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
# verify class_labels
expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
# verify masks
expected_masks_sum = 822873
relative_error = torch.abs(encoding["labels"][0]["masks"].sum() - expected_masks_sum) / expected_masks_sum
self.assertTrue(relative_error < 1e-3)
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
# verify size
expected_size = torch.tensor([800, 1066])
self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
@slow
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_panoptic_annotations with Detr->GroundingDino