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

Add Fast Conditional-DETR Processor (#37071)

Browse Source 
* Add Fast Conditional-DETR Processor

* Update image_processing_conditional_detr_fast.py

* Add modular_conditional_detr.py

* Update image_processing_conditional_detr_fast.py

* Update tests

* make fix

---------

Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
This commit is contained in:
Parteek
2025-04-15 22:03:34 +05:30
committed by GitHub
parent 4f1dbe8152
commit 51f544a4d4
7 changed files with 1310 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

169
tests/models/conditional_detr/test_image_processing_conditional_detr.py
View File

@@ -20,7 +20,7 @@ import unittest
import numpy as np
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
@@ -33,6 +33,9 @@ if is_vision_available():
from transformers import ConditionalDetrImageProcessor
if is_torchvision_available():
from transformers import ConditionalDetrImageProcessorFast
class ConditionalDetrImageProcessingTester:
def __init__(
@@ -132,6 +135,7 @@ class ConditionalDetrImageProcessingTester:
@require_vision
class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixin, unittest.TestCase):
image_processing_class = ConditionalDetrImageProcessor if is_vision_available() else None
fast_image_processing_class = ConditionalDetrImageProcessorFast if is_torchvision_available() else None
def setUp(self):
super().setUp()
@@ -142,23 +146,25 @@ class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcess
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)
@slow
def test_call_pytorch_with_coco_detection_annotations(self):
@@ -169,40 +175,41 @@ class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcess
target = {"image_id": 39769, "annotations": target}
# encode them
image_processing = ConditionalDetrImageProcessor.from_pretrained("microsoft/conditional-detr-resnet-50")
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("microsoft/conditional-detr-resnet-50")
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])
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([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
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, 1066])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
# verify area
expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
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, 1066])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
@slow
def test_call_pytorch_with_coco_panoptic_annotations(self):
@@ -215,43 +222,45 @@ class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcess
masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
# encode them
image_processing = ConditionalDetrImageProcessor(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])
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([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
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 = 822873
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, 1066])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
# verify area
expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
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 = 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])
torch.testing.assert_close(encoding["labels"][0]["orig_size"], expected_orig_size)
# verify size
expected_size = torch.tensor([800, 1066])
torch.testing.assert_close(encoding["labels"][0]["size"], expected_size)
@slow
# Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_detection_annotations with Detr->ConditionalDetr, facebook/detr-resnet-50 ->microsoft/conditional-detr-resnet-50