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

Add fixed resize and pad strategy for object detection (#30742)

Browse Source 
* Add resize and pad strategy

* Merge get_size functions

* Add pad_size + tests to object detection models

* Fixup

* Update docstrings

* Fixup
This commit is contained in:
Pavel Iakubovskii
2024-05-17 16:21:26 +01:00
committed by GitHub
parent e9a8041d1c
commit bf646fbf2d
13 changed files with 929 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
tests/models/conditional_detr/test_image_processing_conditional_detr.py
View File

@@ -490,3 +490,50 @@ class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcess
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1))
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_max_width_max_height_resizing_and_pad_strategy with Detr->ConditionalDetr
def test_max_width_max_height_resizing_and_pad_strategy(self):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = ConditionalDetrImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = ConditionalDetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = ConditionalDetrImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = ConditionalDetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = ConditionalDetrImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))

47
tests/models/deformable_detr/test_image_processing_deformable_detr.py
View File

@@ -492,3 +492,50 @@ class DeformableDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcessi
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1))
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_max_width_max_height_resizing_and_pad_strategy with Detr->DeformableDetr
def test_max_width_max_height_resizing_and_pad_strategy(self):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = DeformableDetrImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = DeformableDetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = DeformableDetrImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = DeformableDetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = DeformableDetrImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))

47
tests/models/deta/test_image_processing_deta.py
View File

@@ -486,3 +486,50 @@ class DetaImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixi
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1))
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_max_width_max_height_resizing_and_pad_strategy with Detr->Deta
def test_max_width_max_height_resizing_and_pad_strategy(self):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = DetaImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = DetaImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = DetaImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = DetaImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = DetaImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))

46
tests/models/detr/test_image_processing_detr.py
View File

@@ -547,3 +547,49 @@ class DetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixi
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1))
def test_max_width_max_height_resizing_and_pad_strategy(self):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = DetrImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = DetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = DetrImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = DetrImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = DetrImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))

47
tests/models/grounding_dino/test_image_processing_grounding_dino.py
View File

@@ -528,3 +528,50 @@ class GroundingDinoImageProcessingTest(AnnotationFormatTestMixin, ImageProcessin
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1))
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_max_width_max_height_resizing_and_pad_strategy with Detr->GroundingDino
def test_max_width_max_height_resizing_and_pad_strategy(self):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = GroundingDinoImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = GroundingDinoImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = GroundingDinoImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = GroundingDinoImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = GroundingDinoImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))

47
tests/models/yolos/test_image_processing_yolos.py
View File

@@ -546,3 +546,50 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
).T
self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1))
self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_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):
image_1 = torch.ones([200, 100, 3], dtype=torch.uint8)
# do_pad=False, max_height=100, max_width=100, image=200x100 -> 100x50
image_processor = YolosImageProcessor(
size={"max_height": 100, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 50]))
# do_pad=False, max_height=300, max_width=100, image=200x100 -> 200x100
image_processor = YolosImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
# do_pad=True, max_height=100, max_width=100, image=200x100 -> 100x100
image_processor = YolosImageProcessor(
size={"max_height": 100, "max_width": 100}, do_pad=True, pad_size={"height": 100, "width": 100}
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 100, 100]))
# do_pad=True, max_height=300, max_width=100, image=200x100 -> 300x100
image_processor = YolosImageProcessor(
size={"max_height": 300, "max_width": 100},
do_pad=True,
pad_size={"height": 301, "width": 101},
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 301, 101]))
### Check for batch
image_2 = torch.ones([100, 150, 3], dtype=torch.uint8)
# do_pad=True, max_height=150, max_width=100, images=[200x100, 100x150] -> 150x100
image_processor = YolosImageProcessor(
size={"max_height": 150, "max_width": 100},
do_pad=True,
pad_size={"height": 150, "width": 100},
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))