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

Add Fast Yolos Processor (#37292)

Browse Source 
* Add Fast Yolos Processor

* Update modular file

* Fix copies

---------

Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
This commit is contained in:
Parteek
2025-04-15 17:53:08 +05:30
committed by GitHub
parent ecaeee66bc
commit f6c79f767c
6 changed files with 1373 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

547
tests/models/yolos/test_image_processing_yolos.py
View File

@@ -21,7 +21,7 @@ import numpy as np
from parameterized import parameterized
from transformers.testing_utils import require_torch, require_vision, slow
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 AnnotationFormatTestMixin, ImageProcessingTestMixin, prepare_image_inputs
@@ -34,6 +34,9 @@ if is_vision_available():
from transformers import YolosImageProcessor
if is_torchvision_available():
from transformers import YolosImageProcessorFast
class YolosImageProcessingTester:
def __init__(
@@ -143,6 +146,7 @@ class YolosImageProcessingTester:
@require_vision
class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixin, unittest.TestCase):
image_processing_class = YolosImageProcessor if is_vision_available() else None
fast_image_processing_class = YolosImageProcessorFast if is_torchvision_available() else None
def setUp(self):
super().setUp()
@@ -153,23 +157,25 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
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, "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, "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, "size"))
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_equivalence_padding(self):
# Initialize image_processings
@@ -199,21 +205,22 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
]
)
def test_resize_max_size_respected(self, image_size, longest_edge, shortest_edge):
image_processor = self.image_processing_class(**self.image_processor_dict)
for image_processing_class in self.image_processor_list:
image_processor = image_processing_class(**self.image_processor_dict)
# create torch tensors as image
image = torch.randint(0, 256, image_size, dtype=torch.uint8)
processed_image = image_processor(
image,
size={"longest_edge": longest_edge, "shortest_edge": shortest_edge},
do_pad=False,
return_tensors="pt",
)["pixel_values"]
# create torch tensors as image
image = torch.randint(0, 256, image_size, dtype=torch.uint8)
processed_image = image_processor(
image,
size={"longest_edge": longest_edge, "shortest_edge": shortest_edge},
do_pad=False,
return_tensors="pt",
)["pixel_values"]
shape = list(processed_image.shape[-2:])
max_size, min_size = max(shape), min(shape)
self.assertTrue(max_size <= 1333, f"Expected max_size <= 1333, got image shape {shape}")
self.assertTrue(min_size <= 800, f"Expected min_size <= 800, got image shape {shape}")
shape = list(processed_image.shape[-2:])
max_size, min_size = max(shape), min(shape)
self.assertTrue(max_size <= 1333, f"Expected max_size <= 1333, got image shape {shape}")
self.assertTrue(min_size <= 800, f"Expected min_size <= 800, got image shape {shape}")
@slow
def test_call_pytorch_with_coco_detection_annotations(self):
@@ -224,40 +231,41 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
target = {"image_id": 39769, "annotations": target}
# encode them
image_processing = YolosImageProcessor.from_pretrained("hustvl/yolos-small")
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.from_pretrained("hustvl/yolos-small")
encoding = image_processing(images=image, annotations=target, return_tensors="pt")
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1056])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1056])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
torch.testing.assert_close(encoding["pixel_values"][0, 0, 0, :3], expected_slice, rtol=1e-4, atol=1e-4)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
torch.testing.assert_close(encoding["pixel_values"][0, 0, 0, :3], expected_slice, rtol=1e-4, atol=1e-4)
# verify area
expected_area = torch.tensor([5832.7256, 11144.6689, 484763.2500, 829269.8125, 146579.4531, 164177.6250])
torch.testing.assert_close(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])
torch.testing.assert_close(encoding["labels"][0]["boxes"][0], expected_boxes_slice, rtol=1e-3, atol=1e-3)
# verify image_id
expected_image_id = torch.tensor([39769])
torch.testing.assert_close(encoding["labels"][0]["image_id"], expected_image_id)
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
torch.testing.assert_close(encoding["labels"][0]["iscrowd"], expected_is_crowd)
# verify class_labels
expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
torch.testing.assert_close(encoding["labels"][0]["class_labels"], expected_class_labels)
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
torch.testing.assert_close(encoding["labels"][0]["orig_size"], expected_orig_size)
# verify size
expected_size = torch.tensor([800, 1056])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
# verify area
expected_area = torch.tensor([5832.7256, 11144.6689, 484763.2500, 829269.8125, 146579.4531, 164177.6250])
torch.testing.assert_close(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])
torch.testing.assert_close(encoding["labels"][0]["boxes"][0], expected_boxes_slice, rtol=1e-3, atol=1e-3)
# verify image_id
expected_image_id = torch.tensor([39769])
torch.testing.assert_close(encoding["labels"][0]["image_id"], expected_image_id)
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
torch.testing.assert_close(encoding["labels"][0]["iscrowd"], expected_is_crowd)
# verify class_labels
expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
torch.testing.assert_close(encoding["labels"][0]["class_labels"], expected_class_labels)
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
torch.testing.assert_close(encoding["labels"][0]["orig_size"], expected_orig_size)
# verify size
expected_size = torch.tensor([800, 1056])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
@slow
def test_call_pytorch_with_coco_panoptic_annotations(self):
@@ -270,43 +278,45 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
# encode them
image_processing = YolosImageProcessor(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, 1056])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# verify pixel values
expected_shape = torch.Size([1, 3, 800, 1056])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
torch.testing.assert_close(encoding["pixel_values"][0, 0, 0, :3], expected_slice, rtol=1e-4, atol=1e-4)
expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
torch.testing.assert_close(encoding["pixel_values"][0, 0, 0, :3], expected_slice, rtol=1e-4, atol=1e-4)
# verify area
expected_area = torch.tensor([146591.5000, 163974.2500, 480092.2500, 11187.0000, 5824.5000, 7562.5000])
torch.testing.assert_close(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])
torch.testing.assert_close(encoding["labels"][0]["boxes"][0], expected_boxes_slice, rtol=1e-3, atol=1e-3)
# verify image_id
expected_image_id = torch.tensor([39769])
torch.testing.assert_close(encoding["labels"][0]["image_id"], expected_image_id)
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
torch.testing.assert_close(encoding["labels"][0]["iscrowd"], expected_is_crowd)
# verify class_labels
expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
torch.testing.assert_close(encoding["labels"][0]["class_labels"], expected_class_labels)
# verify masks
expected_masks_sum = 815161
self.assertEqual(encoding["labels"][0]["masks"].sum().item(), expected_masks_sum)
# verify orig_size
expected_orig_size = torch.tensor([480, 640])
torch.testing.assert_close(encoding["labels"][0]["orig_size"], expected_orig_size)
# verify size
expected_size = torch.tensor([800, 1056])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
# verify area
expected_area = torch.tensor([146591.5000, 163974.2500, 480092.2500, 11187.0000, 5824.5000, 7562.5000])
torch.testing.assert_close(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])
torch.testing.assert_close(encoding["labels"][0]["boxes"][0], expected_boxes_slice, rtol=1e-3, atol=1e-3)
# verify image_id
expected_image_id = torch.tensor([39769])
torch.testing.assert_close(encoding["labels"][0]["image_id"], expected_image_id)
# verify is_crowd
expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
torch.testing.assert_close(encoding["labels"][0]["iscrowd"], expected_is_crowd)
# verify class_labels
expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
torch.testing.assert_close(encoding["labels"][0]["class_labels"], expected_class_labels)
# verify masks
expected_masks_sum = 815161
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])
torch.testing.assert_close(encoding["labels"][0]["orig_size"], expected_orig_size)
# verify size
expected_size = torch.tensor([800, 1056])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
# Output size is slight different from DETR as yolos takes mod of 16
@slow
@@ -336,96 +346,97 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
images = [image_0, image_1]
annotations = [annotations_0, annotations_1]
image_processing = YolosImageProcessor()
encoding = image_processing(
images=images,
annotations=annotations,
return_segmentation_masks=True,
return_tensors="pt", # do_convert_annotations=True
)
for image_processing_class in self.image_processor_list:
image_processing = image_processing_class()
encoding = image_processing(
images=images,
annotations=annotations,
return_segmentation_masks=True,
return_tensors="pt", # do_convert_annotations=True
)
# Check the pixel values have been padded
postprocessed_height, postprocessed_width = 800, 1056
expected_shape = torch.Size([2, 3, postprocessed_height, postprocessed_width])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# Check the pixel values have been padded
postprocessed_height, postprocessed_width = 800, 1056
expected_shape = torch.Size([2, 3, postprocessed_height, postprocessed_width])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# Check the bounding boxes have been adjusted for padded images
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
expected_boxes_0 = torch.tensor(
[
[0.6879, 0.4609, 0.0755, 0.3691],
[0.2118, 0.3359, 0.2601, 0.1566],
[0.5011, 0.5000, 0.9979, 1.0000],
[0.5010, 0.5020, 0.9979, 0.9959],
[0.3284, 0.5944, 0.5884, 0.8112],
[0.8394, 0.5445, 0.3213, 0.9110],
]
)
expected_boxes_1 = torch.tensor(
[
[0.4169, 0.2765, 0.0458, 0.2215],
[0.1284, 0.2016, 0.1576, 0.0940],
[0.3792, 0.4933, 0.7559, 0.9865],
[0.3794, 0.5002, 0.7563, 0.9955],
[0.1990, 0.5456, 0.3566, 0.8646],
[0.5845, 0.4115, 0.3462, 0.7161],
]
)
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3, atol=1e-3)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3, atol=1e-3)
# Check the bounding boxes have been adjusted for padded images
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
expected_boxes_0 = torch.tensor(
[
[0.6879, 0.4609, 0.0755, 0.3691],
[0.2118, 0.3359, 0.2601, 0.1566],
[0.5011, 0.5000, 0.9979, 1.0000],
[0.5010, 0.5020, 0.9979, 0.9959],
[0.3284, 0.5944, 0.5884, 0.8112],
[0.8394, 0.5445, 0.3213, 0.9110],
]
)
expected_boxes_1 = torch.tensor(
[
[0.4169, 0.2765, 0.0458, 0.2215],
[0.1284, 0.2016, 0.1576, 0.0940],
[0.3792, 0.4933, 0.7559, 0.9865],
[0.3794, 0.5002, 0.7563, 0.9955],
[0.1990, 0.5456, 0.3566, 0.8646],
[0.5845, 0.4115, 0.3462, 0.7161],
]
)
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3, atol=1e-3)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3, atol=1e-3)
# Check the masks have also been padded
self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1056]))
self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1056]))
# Check the masks have also been padded
self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1056]))
self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1056]))
# Check if do_convert_annotations=False, then the annotations are not converted to centre_x, centre_y, width, height
# format and not in the range [0, 1]
encoding = image_processing(
images=images,
annotations=annotations,
return_segmentation_masks=True,
do_convert_annotations=False,
return_tensors="pt",
)
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
# Convert to absolute coordinates
unnormalized_boxes_0 = torch.vstack(
[
expected_boxes_0[:, 0] * postprocessed_width,
expected_boxes_0[:, 1] * postprocessed_height,
expected_boxes_0[:, 2] * postprocessed_width,
expected_boxes_0[:, 3] * postprocessed_height,
]
).T
unnormalized_boxes_1 = torch.vstack(
[
expected_boxes_1[:, 0] * postprocessed_width,
expected_boxes_1[:, 1] * postprocessed_height,
expected_boxes_1[:, 2] * postprocessed_width,
expected_boxes_1[:, 3] * postprocessed_height,
]
).T
# Convert from centre_x, centre_y, width, height to x_min, y_min, x_max, y_max
expected_boxes_0 = torch.vstack(
[
unnormalized_boxes_0[:, 0] - unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] - unnormalized_boxes_0[:, 3] / 2,
unnormalized_boxes_0[:, 0] + unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] + unnormalized_boxes_0[:, 3] / 2,
]
).T
expected_boxes_1 = torch.vstack(
[
unnormalized_boxes_1[:, 0] - unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] - unnormalized_boxes_1[:, 3] / 2,
unnormalized_boxes_1[:, 0] + unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] + unnormalized_boxes_1[:, 3] / 2,
]
).T
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1, atol=1)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1, atol=1)
# Check if do_convert_annotations=False, then the annotations are not converted to centre_x, centre_y, width, height
# format and not in the range [0, 1]
encoding = image_processing(
images=images,
annotations=annotations,
return_segmentation_masks=True,
do_convert_annotations=False,
return_tensors="pt",
)
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
# Convert to absolute coordinates
unnormalized_boxes_0 = torch.vstack(
[
expected_boxes_0[:, 0] * postprocessed_width,
expected_boxes_0[:, 1] * postprocessed_height,
expected_boxes_0[:, 2] * postprocessed_width,
expected_boxes_0[:, 3] * postprocessed_height,
]
).T
unnormalized_boxes_1 = torch.vstack(
[
expected_boxes_1[:, 0] * postprocessed_width,
expected_boxes_1[:, 1] * postprocessed_height,
expected_boxes_1[:, 2] * postprocessed_width,
expected_boxes_1[:, 3] * postprocessed_height,
]
).T
# Convert from centre_x, centre_y, width, height to x_min, y_min, x_max, y_max
expected_boxes_0 = torch.vstack(
[
unnormalized_boxes_0[:, 0] - unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] - unnormalized_boxes_0[:, 3] / 2,
unnormalized_boxes_0[:, 0] + unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] + unnormalized_boxes_0[:, 3] / 2,
]
).T
expected_boxes_1 = torch.vstack(
[
unnormalized_boxes_1[:, 0] - unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] - unnormalized_boxes_1[:, 3] / 2,
unnormalized_boxes_1[:, 0] + unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] + unnormalized_boxes_1[:, 3] / 2,
]
).T
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1, atol=1)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1, atol=1)
# Output size is slight different from DETR as yolos takes mod of 16
def test_batched_coco_panoptic_annotations(self):
@@ -457,98 +468,100 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
annotations = [annotation_0, annotation_1]
# encode them
image_processing = YolosImageProcessor(format="coco_panoptic")
encoding = image_processing(
images=images,
annotations=annotations,
masks_path=masks_path,
return_tensors="pt",
return_segmentation_masks=True,
)
for image_processing_class in self.image_processor_list:
image_processing = image_processing_class()
image_processing = YolosImageProcessor(format="coco_panoptic")
encoding = image_processing(
images=images,
annotations=annotations,
masks_path=masks_path,
return_tensors="pt",
return_segmentation_masks=True,
)
# Check the pixel values have been padded
postprocessed_height, postprocessed_width = 800, 1056
expected_shape = torch.Size([2, 3, postprocessed_height, postprocessed_width])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# Check the pixel values have been padded
postprocessed_height, postprocessed_width = 800, 1056
expected_shape = torch.Size([2, 3, postprocessed_height, postprocessed_width])
self.assertEqual(encoding["pixel_values"].shape, expected_shape)
# Check the bounding boxes have been adjusted for padded images
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
expected_boxes_0 = torch.tensor(
[
[0.2625, 0.5437, 0.4688, 0.8625],
[0.7719, 0.4104, 0.4531, 0.7125],
[0.5000, 0.4927, 0.9969, 0.9854],
[0.1688, 0.2000, 0.2063, 0.0917],
[0.5492, 0.2760, 0.0578, 0.2187],
[0.4992, 0.4990, 0.9984, 0.9979],
]
)
expected_boxes_1 = torch.tensor(
[
[0.1591, 0.3262, 0.2841, 0.5175],
[0.4678, 0.2463, 0.2746, 0.4275],
[0.3030, 0.2956, 0.6042, 0.5913],
[0.1023, 0.1200, 0.1250, 0.0550],
[0.3329, 0.1656, 0.0350, 0.1312],
[0.3026, 0.2994, 0.6051, 0.5987],
]
)
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3, atol=1e-3)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3, atol=1e-3)
# Check the bounding boxes have been adjusted for padded images
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
expected_boxes_0 = torch.tensor(
[
[0.2625, 0.5437, 0.4688, 0.8625],
[0.7719, 0.4104, 0.4531, 0.7125],
[0.5000, 0.4927, 0.9969, 0.9854],
[0.1688, 0.2000, 0.2063, 0.0917],
[0.5492, 0.2760, 0.0578, 0.2187],
[0.4992, 0.4990, 0.9984, 0.9979],
]
)
expected_boxes_1 = torch.tensor(
[
[0.1591, 0.3262, 0.2841, 0.5175],
[0.4678, 0.2463, 0.2746, 0.4275],
[0.3030, 0.2956, 0.6042, 0.5913],
[0.1023, 0.1200, 0.1250, 0.0550],
[0.3329, 0.1656, 0.0350, 0.1312],
[0.3026, 0.2994, 0.6051, 0.5987],
]
)
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3, atol=1e-3)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3, atol=1e-3)
# Check the masks have also been padded
self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1056]))
self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1056]))
# Check the masks have also been padded
self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1056]))
self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1056]))
# Check if do_convert_annotations=False, then the annotations are not converted to centre_x, centre_y, width, height
# format and not in the range [0, 1]
encoding = image_processing(
images=images,
annotations=annotations,
masks_path=masks_path,
return_segmentation_masks=True,
do_convert_annotations=False,
return_tensors="pt",
)
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
# Convert to absolute coordinates
unnormalized_boxes_0 = torch.vstack(
[
expected_boxes_0[:, 0] * postprocessed_width,
expected_boxes_0[:, 1] * postprocessed_height,
expected_boxes_0[:, 2] * postprocessed_width,
expected_boxes_0[:, 3] * postprocessed_height,
]
).T
unnormalized_boxes_1 = torch.vstack(
[
expected_boxes_1[:, 0] * postprocessed_width,
expected_boxes_1[:, 1] * postprocessed_height,
expected_boxes_1[:, 2] * postprocessed_width,
expected_boxes_1[:, 3] * postprocessed_height,
]
).T
# Convert from centre_x, centre_y, width, height to x_min, y_min, x_max, y_max
expected_boxes_0 = torch.vstack(
[
unnormalized_boxes_0[:, 0] - unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] - unnormalized_boxes_0[:, 3] / 2,
unnormalized_boxes_0[:, 0] + unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] + unnormalized_boxes_0[:, 3] / 2,
]
).T
expected_boxes_1 = torch.vstack(
[
unnormalized_boxes_1[:, 0] - unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] - unnormalized_boxes_1[:, 3] / 2,
unnormalized_boxes_1[:, 0] + unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] + unnormalized_boxes_1[:, 3] / 2,
]
).T
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, atol=1, rtol=1)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, atol=1, rtol=1)
# Check if do_convert_annotations=False, then the annotations are not converted to centre_x, centre_y, width, height
# format and not in the range [0, 1]
encoding = image_processing(
images=images,
annotations=annotations,
masks_path=masks_path,
return_segmentation_masks=True,
do_convert_annotations=False,
return_tensors="pt",
)
self.assertEqual(encoding["labels"][0]["boxes"].shape, torch.Size([6, 4]))
self.assertEqual(encoding["labels"][1]["boxes"].shape, torch.Size([6, 4]))
# Convert to absolute coordinates
unnormalized_boxes_0 = torch.vstack(
[
expected_boxes_0[:, 0] * postprocessed_width,
expected_boxes_0[:, 1] * postprocessed_height,
expected_boxes_0[:, 2] * postprocessed_width,
expected_boxes_0[:, 3] * postprocessed_height,
]
).T
unnormalized_boxes_1 = torch.vstack(
[
expected_boxes_1[:, 0] * postprocessed_width,
expected_boxes_1[:, 1] * postprocessed_height,
expected_boxes_1[:, 2] * postprocessed_width,
expected_boxes_1[:, 3] * postprocessed_height,
]
).T
# Convert from centre_x, centre_y, width, height to x_min, y_min, x_max, y_max
expected_boxes_0 = torch.vstack(
[
unnormalized_boxes_0[:, 0] - unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] - unnormalized_boxes_0[:, 3] / 2,
unnormalized_boxes_0[:, 0] + unnormalized_boxes_0[:, 2] / 2,
unnormalized_boxes_0[:, 1] + unnormalized_boxes_0[:, 3] / 2,
]
).T
expected_boxes_1 = torch.vstack(
[
unnormalized_boxes_1[:, 0] - unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] - unnormalized_boxes_1[:, 3] / 2,
unnormalized_boxes_1[:, 0] + unnormalized_boxes_1[:, 2] / 2,
unnormalized_boxes_1[:, 1] + unnormalized_boxes_1[:, 3] / 2,
]
).T
torch.testing.assert_close(encoding["labels"][0]["boxes"], expected_boxes_0, atol=1, rtol=1)
torch.testing.assert_close(encoding["labels"][1]["boxes"], expected_boxes_1, atol=1, rtol=1)
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_max_width_max_height_resizing_and_pad_strategy with Detr->Yolos
def test_max_width_max_height_resizing_and_pad_strategy(self):