[fix] Add DeformableDetrFeatureExtractor (#19140)

* Add DeformableDetrFeatureExtractor

* Fix post_process

* Fix name

* Add tests for feature extractor

* Fix doc tests

* Fix name

* Address comments

* Apply same fix to DETR and YOLOS as well
Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>

docs/source/en/model_doc/deformable_detr.mdx

@@ -33,6 +33,16 @@ alt="drawing" width="600"/>
 
 This model was contributed by [nielsr](https://huggingface.co/nielsr). The original code can be found [here](https://github.com/fundamentalvision/Deformable-DETR).
 
+## DeformableDetrFeatureExtractor
+
+[[autodoc]] DeformableDetrFeatureExtractor
+    - __call__
+    - pad_and_create_pixel_mask
+    - post_process
+    - post_process_segmentation
+    - post_process_panoptic
+
+
 ## DeformableDetrConfig
 
 [[autodoc]] DeformableDetrConfig

src/transformers/__init__.py

@@ -659,6 +659,7 @@ else:
     _import_structure["models.beit"].append("BeitFeatureExtractor")
     _import_structure["models.clip"].append("CLIPFeatureExtractor")
     _import_structure["models.convnext"].append("ConvNextFeatureExtractor")
+    _import_structure["models.deformable_detr"].append("DeformableDetrFeatureExtractor")
     _import_structure["models.deit"].append("DeiTFeatureExtractor")
     _import_structure["models.detr"].append("DetrFeatureExtractor")
     _import_structure["models.conditional_detr"].append("ConditionalDetrFeatureExtractor")
@@ -3512,6 +3513,7 @@ if TYPE_CHECKING:
         from .models.clip import CLIPFeatureExtractor
         from .models.conditional_detr import ConditionalDetrFeatureExtractor
         from .models.convnext import ConvNextFeatureExtractor
+        from .models.deformable_detr import DeformableDetrFeatureExtractor
         from .models.deit import DeiTFeatureExtractor
         from .models.detr import DetrFeatureExtractor
         from .models.donut import DonutFeatureExtractor

src/transformers/models/auto/feature_extraction_auto.py

@@ -44,7 +44,7 @@ FEATURE_EXTRACTOR_MAPPING_NAMES = OrderedDict(
         ("cvt", "ConvNextFeatureExtractor"),
         ("data2vec-audio", "Wav2Vec2FeatureExtractor"),
         ("data2vec-vision", "BeitFeatureExtractor"),
-        ("deformable_detr", "DetrFeatureExtractor"),
+        ("deformable_detr", "DeformableDetrFeatureExtractor"),
         ("deit", "DeiTFeatureExtractor"),
         ("detr", "DetrFeatureExtractor"),
         ("donut", "DonutFeatureExtractor"),

src/transformers/models/deformable_detr/__init__.py

@@ -18,13 +18,21 @@
 
 from typing import TYPE_CHECKING
 
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_timm_available
+from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_timm_available, is_vision_available
 
 
 _import_structure = {
     "configuration_deformable_detr": ["DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP", "DeformableDetrConfig"],
 }
 
+try:
+    if not is_vision_available():
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    pass
+else:
+    _import_structure["feature_extraction_deformable_detr"] = ["DeformableDetrFeatureExtractor"]
+
 try:
     if not is_timm_available():
         raise OptionalDependencyNotAvailable()
@@ -42,6 +50,14 @@ else:
 if TYPE_CHECKING:
     from .configuration_deformable_detr import DEFORMABLE_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP, DeformableDetrConfig
 
+    try:
+        if not is_vision_available():
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        pass
+    else:
+        from .feature_extraction_deformable_detr import DeformableDetrFeatureExtractor
+
     try:
         if not is_timm_available():
             raise OptionalDependencyNotAvailable()

src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py

@@ -24,7 +24,7 @@ from PIL import Image
 
 import requests
 from huggingface_hub import cached_download, hf_hub_url
-from transformers import DeformableDetrConfig, DeformableDetrForObjectDetection, DetrFeatureExtractor
+from transformers import DeformableDetrConfig, DeformableDetrFeatureExtractor, DeformableDetrForObjectDetection
 from transformers.utils import logging
 
 
@@ -116,7 +116,7 @@ def convert_deformable_detr_checkpoint(
     config.label2id = {v: k for k, v in id2label.items()}
 
     # load feature extractor
-    feature_extractor = DetrFeatureExtractor(format="coco_detection")
+    feature_extractor = DeformableDetrFeatureExtractor(format="coco_detection")
 
     # prepare image
     img = prepare_img()

src/transformers/models/deformable_detr/modeling_deformable_detr.py

@@ -1884,15 +1884,15 @@ class DeformableDetrForObjectDetection(DeformableDetrPreTrainedModel):
         >>> results = feature_extractor.post_process(outputs, target_sizes=target_sizes)[0]
         >>> for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
         ...     box = [round(i, 2) for i in box.tolist()]
-        ...     # let's only keep detections with score > 0.7
-        ...     if score > 0.7:
+        ...     # let's only keep detections with score > 0.5
+        ...     if score > 0.5:
         ...         print(
         ...             f"Detected {model.config.id2label[label.item()]} with confidence "
         ...             f"{round(score.item(), 3)} at location {box}"
         ...         )
-        Detected cat with confidence 0.856 at location [342.19, 24.3, 640.02, 372.25]
-        Detected remote with confidence 0.739 at location [40.79, 72.78, 176.76, 117.25]
-        Detected cat with confidence 0.859 at location [16.5, 52.84, 318.25, 470.78]
+        Detected cat with confidence 0.8 at location [16.5, 52.84, 318.25, 470.78]
+        Detected cat with confidence 0.789 at location [342.19, 24.3, 640.02, 372.25]
+        Detected remote with confidence 0.633 at location [40.79, 72.78, 176.76, 117.25]
         ```"""
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 

src/transformers/models/detr/feature_extraction_detr.py

@@ -137,7 +137,7 @@ class DetrFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
             sequence like `(width, height)`, output size will be matched to this. If size is an int, smaller edge of
             the image will be matched to this number. i.e, if `height > width`, then image will be rescaled to `(size *
             height / width, size)`.
-        max_size (`int`, *optional*, defaults to `1333`):
+        max_size (`int`, *optional*, defaults to 1333):
             The largest size an image dimension can have (otherwise it's capped). Only has an effect if `do_resize` is
             set to `True`.
         do_normalize (`bool`, *optional*, defaults to `True`):
@@ -683,9 +683,9 @@ class DetrFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
             outputs ([`DetrObjectDetectionOutput`]):
                 Raw outputs of the model.
             target_sizes (`torch.Tensor` of shape `(batch_size, 2)`):
-                Tensor containing the size (h, w) of each image of the batch. For evaluation, this must be the original
-                image size (before any data augmentation). For visualization, this should be the image size after data
-                augment, but before padding.
+                Tensor containing the size (height, width) of each image of the batch. For evaluation, this must be the
+                original image size (before any data augmentation). For visualization, this should be the image size
+                after data augment, but before padding.
 
         Returns:
             `List[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image

src/transformers/models/yolos/feature_extraction_yolos.py

@@ -666,9 +666,9 @@ class YolosFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin)
             outputs ([`DetrObjectDetectionOutput`]):
                 Raw outputs of the model.
             target_sizes (`torch.Tensor` of shape `(batch_size, 2)`):
-                Tensor containing the size (h, w) of each image of the batch. For evaluation, this must be the original
-                image size (before any data augmentation). For visualization, this should be the image size after data
-                augment, but before padding.
+                Tensor containing the size (height, width) of each image of the batch. For evaluation, this must be the
+                original image size (before any data augmentation). For visualization, this should be the image size
+                after data augment, but before padding.
 
         Returns:
             `List[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image

src/transformers/utils/dummy_vision_objects.py

@@ -38,6 +38,13 @@ class ConvNextFeatureExtractor(metaclass=DummyObject):
         requires_backends(self, ["vision"])
 
 
+class DeformableDetrFeatureExtractor(metaclass=DummyObject):
+    _backends = ["vision"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["vision"])
+
+
 class DeiTFeatureExtractor(metaclass=DummyObject):
     _backends = ["vision"]
 

tests/models/deformable_detr/test_feature_extraction_deformable_detr.py

+# coding=utf-8
+# Copyright 2022 HuggingFace Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import json
+import pathlib
+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 ...test_feature_extraction_common import FeatureExtractionSavingTestMixin, prepare_image_inputs
+
+
+if is_torch_available():
+    import torch
+
+if is_vision_available():
+    from PIL import Image
+
+    from transformers import DeformableDetrFeatureExtractor
+
+
+class DeformableDetrFeatureExtractionTester(unittest.TestCase):
+    def __init__(
+        self,
+        parent,
+        batch_size=7,
+        num_channels=3,
+        min_resolution=30,
+        max_resolution=400,
+        do_resize=True,
+        size=18,
+        max_size=1333,  # by setting max_size > max_resolution we're effectively not testing this :p
+        do_normalize=True,
+        image_mean=[0.5, 0.5, 0.5],
+        image_std=[0.5, 0.5, 0.5],
+    ):
+        self.parent = parent
+        self.batch_size = batch_size
+        self.num_channels = num_channels
+        self.min_resolution = min_resolution
+        self.max_resolution = max_resolution
+        self.do_resize = do_resize
+        self.size = size
+        self.max_size = max_size
+        self.do_normalize = do_normalize
+        self.image_mean = image_mean
+        self.image_std = image_std
+
+    def prepare_feat_extract_dict(self):
+        return {
+            "do_resize": self.do_resize,
+            "size": self.size,
+            "max_size": self.max_size,
+            "do_normalize": self.do_normalize,
+            "image_mean": self.image_mean,
+            "image_std": self.image_std,
+        }
+
+    def get_expected_values(self, image_inputs, batched=False):
+        """
+        This function computes the expected height and width when providing images to DeformableDetrFeatureExtractor,
+        assuming do_resize is set to True with a scalar size.
+        """
+        if not batched:
+            image = image_inputs[0]
+            if isinstance(image, Image.Image):
+                w, h = image.size
+            else:
+                h, w = image.shape[1], image.shape[2]
+            if w < h:
+                expected_height = int(self.size * h / w)
+                expected_width = self.size
+            elif w > h:
+                expected_height = self.size
+                expected_width = int(self.size * w / h)
+            else:
+                expected_height = self.size
+                expected_width = self.size
+
+        else:
+            expected_values = []
+            for image in image_inputs:
+                expected_height, expected_width = self.get_expected_values([image])
+                expected_values.append((expected_height, expected_width))
+            expected_height = max(expected_values, key=lambda item: item[0])[0]
+            expected_width = max(expected_values, key=lambda item: item[1])[1]
+
+        return expected_height, expected_width
+
+
+@require_torch
+@require_vision
+class DeformableDetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestCase):
+
+    feature_extraction_class = DeformableDetrFeatureExtractor if is_vision_available() else None
+
+    def setUp(self):
+        self.feature_extract_tester = DeformableDetrFeatureExtractionTester(self)
+
+    @property
+    def feat_extract_dict(self):
+        return self.feature_extract_tester.prepare_feat_extract_dict()
+
+    def test_feat_extract_properties(self):
+        feature_extractor = self.feature_extraction_class(**self.feat_extract_dict)
+        self.assertTrue(hasattr(feature_extractor, "image_mean"))
+        self.assertTrue(hasattr(feature_extractor, "image_std"))
+        self.assertTrue(hasattr(feature_extractor, "do_normalize"))
+        self.assertTrue(hasattr(feature_extractor, "do_resize"))
+        self.assertTrue(hasattr(feature_extractor, "size"))
+        self.assertTrue(hasattr(feature_extractor, "max_size"))
+
+    def test_batch_feature(self):
+        pass
+
+    def test_call_pil(self):
+        # Initialize feature_extractor
+        feature_extractor = self.feature_extraction_class(**self.feat_extract_dict)
+        # create random PIL images
+        image_inputs = prepare_image_inputs(self.feature_extract_tester, equal_resolution=False)
+        for image in image_inputs:
+            self.assertIsInstance(image, Image.Image)
+
+        # Test not batched input
+        encoded_images = feature_extractor(image_inputs[0], return_tensors="pt").pixel_values
+
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs)
+
+        self.assertEqual(
+            encoded_images.shape,
+            (1, self.feature_extract_tester.num_channels, expected_height, expected_width),
+        )
+
+        # Test batched
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs, batched=True)
+
+        encoded_images = feature_extractor(image_inputs, return_tensors="pt").pixel_values
+        self.assertEqual(
+            encoded_images.shape,
+            (
+                self.feature_extract_tester.batch_size,
+                self.feature_extract_tester.num_channels,
+                expected_height,
+                expected_width,
+            ),
+        )
+
+    def test_call_numpy(self):
+        # Initialize feature_extractor
+        feature_extractor = self.feature_extraction_class(**self.feat_extract_dict)
+        # create random numpy tensors
+        image_inputs = prepare_image_inputs(self.feature_extract_tester, equal_resolution=False, numpify=True)
+        for image in image_inputs:
+            self.assertIsInstance(image, np.ndarray)
+
+        # Test not batched input
+        encoded_images = feature_extractor(image_inputs[0], return_tensors="pt").pixel_values
+
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs)
+
+        self.assertEqual(
+            encoded_images.shape,
+            (1, self.feature_extract_tester.num_channels, expected_height, expected_width),
+        )
+
+        # Test batched
+        encoded_images = feature_extractor(image_inputs, return_tensors="pt").pixel_values
+
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs, batched=True)
+
+        self.assertEqual(
+            encoded_images.shape,
+            (
+                self.feature_extract_tester.batch_size,
+                self.feature_extract_tester.num_channels,
+                expected_height,
+                expected_width,
+            ),
+        )
+
+    def test_call_pytorch(self):
+        # Initialize feature_extractor
+        feature_extractor = self.feature_extraction_class(**self.feat_extract_dict)
+        # create random PyTorch tensors
+        image_inputs = prepare_image_inputs(self.feature_extract_tester, equal_resolution=False, torchify=True)
+        for image in image_inputs:
+            self.assertIsInstance(image, torch.Tensor)
+
+        # Test not batched input
+        encoded_images = feature_extractor(image_inputs[0], return_tensors="pt").pixel_values
+
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs)
+
+        self.assertEqual(
+            encoded_images.shape,
+            (1, self.feature_extract_tester.num_channels, expected_height, expected_width),
+        )
+
+        # Test batched
+        encoded_images = feature_extractor(image_inputs, return_tensors="pt").pixel_values
+
+        expected_height, expected_width = self.feature_extract_tester.get_expected_values(image_inputs, batched=True)
+
+        self.assertEqual(
+            encoded_images.shape,
+            (
+                self.feature_extract_tester.batch_size,
+                self.feature_extract_tester.num_channels,
+                expected_height,
+                expected_width,
+            ),
+        )
+
+    def test_equivalence_pad_and_create_pixel_mask(self):
+        # Initialize feature_extractors
+        feature_extractor_1 = self.feature_extraction_class(**self.feat_extract_dict)
+        feature_extractor_2 = self.feature_extraction_class(do_resize=False, do_normalize=False)
+        # create random PyTorch tensors
+        image_inputs = prepare_image_inputs(self.feature_extract_tester, equal_resolution=False, torchify=True)
+        for image in image_inputs:
+            self.assertIsInstance(image, torch.Tensor)
+
+        # Test whether the method "pad_and_return_pixel_mask" and calling the feature extractor return the same tensors
+        encoded_images_with_method = feature_extractor_1.pad_and_create_pixel_mask(image_inputs, return_tensors="pt")
+        encoded_images = feature_extractor_2(image_inputs, return_tensors="pt")
+
+        self.assertTrue(
+            torch.allclose(encoded_images_with_method["pixel_values"], encoded_images["pixel_values"], atol=1e-4)
+        )
+        self.assertTrue(
+            torch.allclose(encoded_images_with_method["pixel_mask"], encoded_images["pixel_mask"], atol=1e-4)
+        )
+
+    @slow
+    def test_call_pytorch_with_coco_detection_annotations(self):
+        # prepare image and target
+        image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        with open("./tests/fixtures/tests_samples/COCO/coco_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        target = {"image_id": 39769, "annotations": target}
+
+        # encode them
+        feature_extractor = DeformableDetrFeatureExtractor()
+        encoding = feature_extractor(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)
+
+        expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
+
+        # verify area
+        expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
+        # verify boxes
+        expected_boxes_shape = torch.Size([6, 4])
+        self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
+        expected_boxes_slice = torch.tensor([0.5503, 0.2765, 0.0604, 0.2215])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
+        # verify image_id
+        expected_image_id = torch.tensor([39769])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
+        # verify is_crowd
+        expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
+        # verify class_labels
+        expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
+        # verify orig_size
+        expected_orig_size = torch.tensor([480, 640])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
+        # verify size
+        expected_size = torch.tensor([800, 1066])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
+
+    @slow
+    def test_call_pytorch_with_coco_panoptic_annotations(self):
+        # prepare image, target and masks_path
+        image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png")
+        with open("./tests/fixtures/tests_samples/COCO/coco_panoptic_annotations.txt", "r") as f:
+            target = json.loads(f.read())
+
+        target = {"file_name": "000000039769.png", "image_id": 39769, "segments_info": target}
+
+        masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
+
+        # encode them
+        feature_extractor = DeformableDetrFeatureExtractor(format="coco_panoptic")
+        encoding = feature_extractor(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)
+
+        expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
+
+        # verify area
+        expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
+        # verify boxes
+        expected_boxes_shape = torch.Size([6, 4])
+        self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
+        expected_boxes_slice = torch.tensor([0.2625, 0.5437, 0.4688, 0.8625])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
+        # verify image_id
+        expected_image_id = torch.tensor([39769])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
+        # verify is_crowd
+        expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
+        # verify class_labels
+        expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
+        # verify masks
+        expected_masks_sum = 822338
+        self.assertEqual(encoding["labels"][0]["masks"].sum().item(), expected_masks_sum)
+        # verify orig_size
+        expected_orig_size = torch.tensor([480, 640])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
+        # verify size
+        expected_size = torch.tensor([800, 1066])
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))

tests/models/detr/test_feature_extraction_detr.py

@@ -240,8 +240,12 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
         encoded_images_with_method = feature_extractor_1.pad_and_create_pixel_mask(image_inputs, return_tensors="pt")
         encoded_images = feature_extractor_2(image_inputs, return_tensors="pt")
 
-        assert torch.allclose(encoded_images_with_method["pixel_values"], encoded_images["pixel_values"], atol=1e-4)
-        assert torch.allclose(encoded_images_with_method["pixel_mask"], encoded_images["pixel_mask"], atol=1e-4)
+        self.assertTrue(
+            torch.allclose(encoded_images_with_method["pixel_values"], encoded_images["pixel_values"], atol=1e-4)
+        )
+        self.assertTrue(
+            torch.allclose(encoded_images_with_method["pixel_mask"], encoded_images["pixel_mask"], atol=1e-4)
+        )
 
     @slow
     def test_call_pytorch_with_coco_detection_annotations(self):
@@ -261,31 +265,31 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
         self.assertEqual(encoding["pixel_values"].shape, expected_shape)
 
         expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
-        assert torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4)
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
 
         # verify area
         expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
-        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
         self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
         expected_boxes_slice = torch.tensor([0.5503, 0.2765, 0.0604, 0.2215])
-        assert torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
         # verify image_id
         expected_image_id = torch.tensor([39769])
-        assert torch.allclose(encoding["labels"][0]["image_id"], expected_image_id)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
         # verify is_crowd
         expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
-        assert torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
         # verify class_labels
         expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
-        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
         # verify orig_size
         expected_orig_size = torch.tensor([480, 640])
-        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["labels"][0]["size"], expected_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
 
     @slow
     def test_call_pytorch_with_coco_panoptic_annotations(self):
@@ -299,8 +303,7 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
         masks_path = pathlib.Path("./tests/fixtures/tests_samples/COCO/coco_panoptic")
 
         # encode them
-        # TODO replace by .from_pretrained facebook/detr-resnet-50-panoptic
-        feature_extractor = DetrFeatureExtractor(format="coco_panoptic")
+        feature_extractor = DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50-panoptic")
         encoding = feature_extractor(images=image, annotations=target, masks_path=masks_path, return_tensors="pt")
 
         # verify pixel values
@@ -308,31 +311,31 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
         self.assertEqual(encoding["pixel_values"].shape, expected_shape)
 
         expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
-        assert torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4)
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
 
         # verify area
         expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
-        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
         self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
         expected_boxes_slice = torch.tensor([0.2625, 0.5437, 0.4688, 0.8625])
-        assert torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
         # verify image_id
         expected_image_id = torch.tensor([39769])
-        assert torch.allclose(encoding["labels"][0]["image_id"], expected_image_id)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
         # verify is_crowd
         expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
-        assert torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
         # verify class_labels
         expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
-        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
         # verify masks
         expected_masks_sum = 822338
         self.assertEqual(encoding["labels"][0]["masks"].sum().item(), expected_masks_sum)
         # verify orig_size
         expected_orig_size = torch.tensor([480, 640])
-        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["labels"][0]["size"], expected_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))

tests/models/yolos/test_feature_extraction_yolos.py

@@ -240,7 +240,9 @@ class YolosFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.Test
         encoded_images_with_method = feature_extractor_1.pad(image_inputs, return_tensors="pt")
         encoded_images = feature_extractor_2(image_inputs, return_tensors="pt")
 
-        assert torch.allclose(encoded_images_with_method["pixel_values"], encoded_images["pixel_values"], atol=1e-4)
+        self.assertTrue(
+            torch.allclose(encoded_images_with_method["pixel_values"], encoded_images["pixel_values"], atol=1e-4)
+        )
 
     @slow
     def test_call_pytorch_with_coco_detection_annotations(self):
@@ -260,31 +262,31 @@ class YolosFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.Test
         self.assertEqual(encoding["pixel_values"].shape, expected_shape)
 
         expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
-        assert torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4)
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
 
         # verify area
         expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
-        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
         self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
         expected_boxes_slice = torch.tensor([0.5503, 0.2765, 0.0604, 0.2215])
-        assert torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
         # verify image_id
         expected_image_id = torch.tensor([39769])
-        assert torch.allclose(encoding["labels"][0]["image_id"], expected_image_id)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
         # verify is_crowd
         expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
-        assert torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
         # verify class_labels
         expected_class_labels = torch.tensor([75, 75, 63, 65, 17, 17])
-        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
         # verify orig_size
         expected_orig_size = torch.tensor([480, 640])
-        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["labels"][0]["size"], expected_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))
 
     @slow
     def test_call_pytorch_with_coco_panoptic_annotations(self):
@@ -306,31 +308,31 @@ class YolosFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.Test
         self.assertEqual(encoding["pixel_values"].shape, expected_shape)
 
         expected_slice = torch.tensor([0.2796, 0.3138, 0.3481])
-        assert torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4)
+        self.assertTrue(torch.allclose(encoding["pixel_values"][0, 0, 0, :3], expected_slice, atol=1e-4))
 
         # verify area
         expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
-        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["area"], expected_area))
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
         self.assertEqual(encoding["labels"][0]["boxes"].shape, expected_boxes_shape)
         expected_boxes_slice = torch.tensor([0.2625, 0.5437, 0.4688, 0.8625])
-        assert torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["boxes"][0], expected_boxes_slice, atol=1e-3))
         # verify image_id
         expected_image_id = torch.tensor([39769])
-        assert torch.allclose(encoding["labels"][0]["image_id"], expected_image_id)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["image_id"], expected_image_id))
         # verify is_crowd
         expected_is_crowd = torch.tensor([0, 0, 0, 0, 0, 0])
-        assert torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["iscrowd"], expected_is_crowd))
         # verify class_labels
         expected_class_labels = torch.tensor([17, 17, 63, 75, 75, 93])
-        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels))
         # verify masks
         expected_masks_sum = 822338
         self.assertEqual(encoding["labels"][0]["masks"].sum().item(), expected_masks_sum)
         # verify orig_size
         expected_orig_size = torch.tensor([480, 640])
-        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size))
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["labels"][0]["size"], expected_size)
+        self.assertTrue(torch.allclose(encoding["labels"][0]["size"], expected_size))