[DETR] Update the processing to adapt masks & bboxes to reflect padding (#28363)

* Update the processing so bbox coords are adjusted for padding

* Just pad masks

* Tidy up, add tests

* Better tests

* Fix yolos and mark as slow for pycocotols

* Fix yolos - return_tensors

* Clarify padding and normalization behaviour

tests/models/conditional_detr/test_image_processing_conditional_detr.py

@@ -248,3 +248,246 @@ class ConditionalDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcess
         # 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->ConditionalDetr, facebook/detr-resnet-50 ->microsoft/conditional-detr-resnet-50
+    def test_batched_coco_detection_annotations(self):
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotations_0 = {"image_id": 39769, "annotations": target}
+        annotations_1 = {"image_id": 39769, "annotations": target}
+
+        # Adjust the bounding boxes for the resized image
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotations_1["annotations"])):
+            coords = annotations_1["annotations"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotations_1["annotations"][i]["bbox"] = new_bbox
+
+        images = [image_0, image_1]
+        annotations = [annotations_0, annotations_1]
+
+        image_processing = ConditionalDetrImageProcessor()
+        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, 1066
+        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(
+            [
+                [0.4130, 0.2765, 0.0453, 0.2215],
+                [0.1272, 0.2016, 0.1561, 0.0940],
+                [0.3757, 0.4933, 0.7488, 0.9865],
+                [0.3759, 0.5002, 0.7492, 0.9955],
+                [0.1971, 0.5456, 0.3532, 0.8646],
+                [0.5790, 0.4115, 0.3430, 0.7161],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))
+
+    @slow
+    # Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_panoptic_annotations with Detr->ConditionalDetr
+    def test_batched_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotation_0 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+        annotation_1 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotation_1["segments_info"])):
+            coords = annotation_1["segments_info"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotation_1["segments_info"][i]["bbox"] = new_bbox
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        images = [image_0, image_1]
+        annotations = [annotation_0, annotation_1]
+
+        # encode them
+        image_processing = ConditionalDetrImageProcessor(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, 1066
+        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(
+            [
+                [0.1576, 0.3262, 0.2814, 0.5175],
+                [0.4634, 0.2463, 0.2720, 0.4275],
+                [0.3002, 0.2956, 0.5985, 0.5913],
+                [0.1013, 0.1200, 0.1238, 0.0550],
+                [0.3297, 0.1656, 0.0347, 0.1312],
+                [0.2997, 0.2994, 0.5994, 0.5987],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))

tests/models/deformable_detr/test_image_processing_deformable_detr.py

@@ -250,3 +250,246 @@ class DeformableDetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcessi
         # 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->DeformableDetr
+    def test_batched_coco_detection_annotations(self):
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotations_0 = {"image_id": 39769, "annotations": target}
+        annotations_1 = {"image_id": 39769, "annotations": target}
+
+        # Adjust the bounding boxes for the resized image
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotations_1["annotations"])):
+            coords = annotations_1["annotations"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotations_1["annotations"][i]["bbox"] = new_bbox
+
+        images = [image_0, image_1]
+        annotations = [annotations_0, annotations_1]
+
+        image_processing = DeformableDetrImageProcessor()
+        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, 1066
+        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(
+            [
+                [0.4130, 0.2765, 0.0453, 0.2215],
+                [0.1272, 0.2016, 0.1561, 0.0940],
+                [0.3757, 0.4933, 0.7488, 0.9865],
+                [0.3759, 0.5002, 0.7492, 0.9955],
+                [0.1971, 0.5456, 0.3532, 0.8646],
+                [0.5790, 0.4115, 0.3430, 0.7161],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))
+
+    @slow
+    # Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_panoptic_annotations with Detr->DeformableDetr
+    def test_batched_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotation_0 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+        annotation_1 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotation_1["segments_info"])):
+            coords = annotation_1["segments_info"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotation_1["segments_info"][i]["bbox"] = new_bbox
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        images = [image_0, image_1]
+        annotations = [annotation_0, annotation_1]
+
+        # encode them
+        image_processing = DeformableDetrImageProcessor(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, 1066
+        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(
+            [
+                [0.1576, 0.3262, 0.2814, 0.5175],
+                [0.4634, 0.2463, 0.2720, 0.4275],
+                [0.3002, 0.2956, 0.5985, 0.5913],
+                [0.1013, 0.1200, 0.1238, 0.0550],
+                [0.3297, 0.1656, 0.0347, 0.1312],
+                [0.2997, 0.2994, 0.5994, 0.5987],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))

tests/models/deta/test_image_processing_deta.py

@@ -244,3 +244,246 @@ class DetaImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixi
         # 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->Deta
+    def test_batched_coco_detection_annotations(self):
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotations_0 = {"image_id": 39769, "annotations": target}
+        annotations_1 = {"image_id": 39769, "annotations": target}
+
+        # Adjust the bounding boxes for the resized image
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotations_1["annotations"])):
+            coords = annotations_1["annotations"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotations_1["annotations"][i]["bbox"] = new_bbox
+
+        images = [image_0, image_1]
+        annotations = [annotations_0, annotations_1]
+
+        image_processing = DetaImageProcessor()
+        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, 1066
+        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(
+            [
+                [0.4130, 0.2765, 0.0453, 0.2215],
+                [0.1272, 0.2016, 0.1561, 0.0940],
+                [0.3757, 0.4933, 0.7488, 0.9865],
+                [0.3759, 0.5002, 0.7492, 0.9955],
+                [0.1971, 0.5456, 0.3532, 0.8646],
+                [0.5790, 0.4115, 0.3430, 0.7161],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))
+
+    @slow
+    # Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_panoptic_annotations with Detr->Deta
+    def test_batched_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotation_0 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+        annotation_1 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotation_1["segments_info"])):
+            coords = annotation_1["segments_info"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotation_1["segments_info"][i]["bbox"] = new_bbox
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        images = [image_0, image_1]
+        annotations = [annotation_0, annotation_1]
+
+        # encode them
+        image_processing = DetaImageProcessor(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, 1066
+        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(
+            [
+                [0.1576, 0.3262, 0.2814, 0.5175],
+                [0.4634, 0.2463, 0.2720, 0.4275],
+                [0.3002, 0.2956, 0.5985, 0.5913],
+                [0.1013, 0.1200, 0.1238, 0.0550],
+                [0.3297, 0.1656, 0.0347, 0.1312],
+                [0.2997, 0.2994, 0.5994, 0.5987],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))

tests/models/detr/test_image_processing_detr.py

@@ -13,7 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import json
 import pathlib
 import unittest
@@ -308,3 +307,244 @@ class DetrImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMixi
         # verify size
         expected_size = torch.tensor([800, 1066])
         self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
+
+    @slow
+    def test_batched_coco_detection_annotations(self):
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotations_0 = {"image_id": 39769, "annotations": target}
+        annotations_1 = {"image_id": 39769, "annotations": target}
+
+        # Adjust the bounding boxes for the resized image
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotations_1["annotations"])):
+            coords = annotations_1["annotations"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotations_1["annotations"][i]["bbox"] = new_bbox
+
+        images = [image_0, image_1]
+        annotations = [annotations_0, annotations_1]
+
+        image_processing = DetrImageProcessor()
+        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, 1066
+        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(
+            [
+                [0.4130, 0.2765, 0.0453, 0.2215],
+                [0.1272, 0.2016, 0.1561, 0.0940],
+                [0.3757, 0.4933, 0.7488, 0.9865],
+                [0.3759, 0.5002, 0.7492, 0.9955],
+                [0.1971, 0.5456, 0.3532, 0.8646],
+                [0.5790, 0.4115, 0.3430, 0.7161],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))
+
+    @slow
+    def test_batched_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotation_0 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+        annotation_1 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotation_1["segments_info"])):
+            coords = annotation_1["segments_info"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotation_1["segments_info"][i]["bbox"] = new_bbox
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        images = [image_0, image_1]
+        annotations = [annotation_0, annotation_1]
+
+        # encode them
+        image_processing = DetrImageProcessor(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, 1066
+        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(
+            [
+                [0.1576, 0.3262, 0.2814, 0.5175],
+                [0.4634, 0.2463, 0.2720, 0.4275],
+                [0.3002, 0.2956, 0.5985, 0.5913],
+                [0.1013, 0.1200, 0.1238, 0.0550],
+                [0.3297, 0.1656, 0.0347, 0.1312],
+                [0.2997, 0.2994, 0.5994, 0.5987],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))

tests/models/yolos/test_image_processing_yolos.py

@@ -287,3 +287,246 @@ class YolosImageProcessingTest(AnnotationFormatTestMixin, ImageProcessingTestMix
         # verify size
         expected_size = torch.tensor([800, 1056])
         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->Yolos
+    def test_batched_coco_detection_annotations(self):
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotations_0 = {"image_id": 39769, "annotations": target}
+        annotations_1 = {"image_id": 39769, "annotations": target}
+
+        # Adjust the bounding boxes for the resized image
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotations_1["annotations"])):
+            coords = annotations_1["annotations"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotations_1["annotations"][i]["bbox"] = new_bbox
+
+        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
+        )
+
+        # Check the pixel values have been padded
+        postprocessed_height, postprocessed_width = 800, 1066
+        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(
+            [
+                [0.4130, 0.2765, 0.0453, 0.2215],
+                [0.1272, 0.2016, 0.1561, 0.0940],
+                [0.3757, 0.4933, 0.7488, 0.9865],
+                [0.3759, 0.5002, 0.7492, 0.9955],
+                [0.1971, 0.5456, 0.3532, 0.8646],
+                [0.5790, 0.4115, 0.3430, 0.7161],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))
+
+    @slow
+    # Copied from tests.models.detr.test_image_processing_detr.DetrImageProcessingTest.test_batched_coco_panoptic_annotations with Detr->Yolos
+    def test_batched_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image_0 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        image_1 = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png").resize((800, 800))
+
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        annotation_0 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+        annotation_1 = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        w_0, h_0 = image_0.size
+        w_1, h_1 = image_1.size
+        for i in range(len(annotation_1["segments_info"])):
+            coords = annotation_1["segments_info"][i]["bbox"]
+            new_bbox = [
+                coords[0] * w_1 / w_0,
+                coords[1] * h_1 / h_0,
+                coords[2] * w_1 / w_0,
+                coords[3] * h_1 / h_0,
+            ]
+            annotation_1["segments_info"][i]["bbox"] = new_bbox
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        images = [image_0, image_1]
+        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,
+        )
+
+        # Check the pixel values have been padded
+        postprocessed_height, postprocessed_width = 800, 1066
+        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(
+            [
+                [0.1576, 0.3262, 0.2814, 0.5175],
+                [0.4634, 0.2463, 0.2720, 0.4275],
+                [0.3002, 0.2956, 0.5985, 0.5913],
+                [0.1013, 0.1200, 0.1238, 0.0550],
+                [0.3297, 0.1656, 0.0347, 0.1312],
+                [0.2997, 0.2994, 0.5994, 0.5987],
+            ]
+        )
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"], expected_boxes_0, rtol=1e-3))
+        self.assertTrue(torch.allclose(encoding["labels"][1]["boxes"], expected_boxes_1, rtol=1e-3))
+
+        # Check the masks have also been padded
+        self.assertEqual(encoding["labels"][0]["masks"].shape, torch.Size([6, 800, 1066]))
+        self.assertEqual(encoding["labels"][1]["masks"].shape, torch.Size([6, 800, 1066]))
+
+        # 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
+        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))