Rename detr targets to labels (#12280)

* Rename target to labels in DetrFeatureExtractor

* Update DetrFeatureExtractor tests accordingly

* Improve docs of DetrFeatureExtractor

* Improve docs

* Make style

src/transformers/models/detr/configuration_detr.py

@@ -64,11 +64,6 @@ class DetrConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities.
         activation_dropout (:obj:`float`, `optional`, defaults to 0.0):
             The dropout ratio for activations inside the fully connected layer.
-        classifier_dropout (:obj:`float`, `optional`, defaults to 0.0):
-            The dropout ratio for classifier.
-        max_position_embeddings (:obj:`int`, `optional`, defaults to 1024):
-            The maximum sequence length that this model might ever be used with. Typically set this to something large
-            just in case (e.g., 512 or 1024 or 2048).
         init_std (:obj:`float`, `optional`, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         init_xavier_std (:obj:`float`, `optional`, defaults to 1):
@@ -178,7 +173,6 @@ class DetrConfig(PretrainedConfig):
         self.init_xavier_std = init_xavier_std
         self.encoder_layerdrop = encoder_layerdrop
         self.decoder_layerdrop = decoder_layerdrop
-        self.classifier_dropout = classifier_dropout
         self.num_hidden_layers = encoder_layers
         self.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True
         self.auxiliary_loss = auxiliary_loss

src/transformers/models/detr/feature_extraction_detr.py

@@ -440,7 +440,8 @@ class DetrFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
                 annotations.
 
             return_segmentation_masks (:obj:`Dict`, :obj:`List[Dict]`, `optional`, defaults to :obj:`False`):
-                Whether to also return instance segmentation masks in case :obj:`format = "coco_detection"`.
+                Whether to also include instance segmentation masks as part of the labels in case :obj:`format =
+                "coco_detection"`.
 
             masks_path (:obj:`pathlib.Path`, `optional`):
                 Path to the directory containing the PNG files that store the class-agnostic image segmentations. Only
@@ -465,6 +466,7 @@ class DetrFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
             - **pixel_values** -- Pixel values to be fed to a model.
             - **pixel_mask** -- Pixel mask to be fed to a model (when :obj:`pad_and_return_pixel_mask=True` or if
               `"pixel_mask"` is in :obj:`self.model_input_names`).
+            - **labels** -- Optional labels to be fed to a model (when :obj:`annotations` are provided)
         """
         # Input type checking for clearer error
 
@@ -613,7 +615,7 @@ class DetrFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
                 if not is_torch_available():
                     raise ImportError("Unable to convert output to PyTorch tensors format, PyTorch is not installed.")
 
-                encoded_inputs["target"] = [
+                encoded_inputs["labels"] = [
                     {k: torch.from_numpy(v) for k, v in target.items()} for target in annotations
                 ]
 

src/transformers/models/detr/modeling_detr.py

@@ -828,8 +828,8 @@ DETR_INPUTS_DOCSTRING = r"""
         pixel_values (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it.
 
-            Pixel values can be obtained using :class:`~transformers.DetrTokenizer`. See
-            :meth:`transformers.DetrTokenizer.__call__` for details.
+            Pixel values can be obtained using :class:`~transformers.DetrFeatureExtractor`. See
+            :meth:`transformers.DetrFeatureExtractor.__call__` for details.
 
         pixel_mask (:obj:`torch.LongTensor` of shape :obj:`(batch_size, height, width)`, `optional`):
             Mask to avoid performing attention on padding pixel values. Mask values selected in ``[0, 1]``:
@@ -990,7 +990,6 @@ class DetrDecoder(DetrPreTrainedModel):
         super().__init__(config)
         self.dropout = config.dropout
         self.layerdrop = config.decoder_layerdrop
-        self.max_target_positions = config.max_position_embeddings
 
         self.layers = nn.ModuleList([DetrDecoderLayer(config) for _ in range(config.decoder_layers)])
         # in DETR, the decoder uses layernorm after the last decoder layer output

tests/test_feature_extraction_detr.py

@@ -253,8 +253,7 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
         target = {"image_id": 39769, "annotations": target}
 
         # encode them
-        # TODO replace by facebook/detr-resnet-50
-        feature_extractor = DetrFeatureExtractor.from_pretrained("nielsr/detr-resnet-50")
+        feature_extractor = DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50")
         encoding = feature_extractor(images=image, annotations=target, return_tensors="pt")
 
         # verify pixel values
@@ -266,27 +265,27 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
 
         # verify area
         expected_area = torch.tensor([5887.9600, 11250.2061, 489353.8438, 837122.7500, 147967.5156, 165732.3438])
-        assert torch.allclose(encoding["target"][0]["area"], expected_area)
+        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
-        self.assertEqual(encoding["target"][0]["boxes"].shape, expected_boxes_shape)
+        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["target"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        assert 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["target"][0]["image_id"], expected_image_id)
+        assert 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["target"][0]["iscrowd"], expected_is_crowd)
+        assert 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["target"][0]["class_labels"], expected_class_labels)
+        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
         # verify orig_size
         expected_orig_size = torch.tensor([480, 640])
-        assert torch.allclose(encoding["target"][0]["orig_size"], expected_orig_size)
+        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["target"][0]["size"], expected_size)
+        assert torch.allclose(encoding["labels"][0]["size"], expected_size)
 
     @slow
     def test_call_pytorch_with_coco_panoptic_annotations(self):
@@ -313,27 +312,27 @@ class DetrFeatureExtractionTest(FeatureExtractionSavingTestMixin, unittest.TestC
 
         # verify area
         expected_area = torch.tensor([147979.6875, 165527.0469, 484638.5938, 11292.9375, 5879.6562, 7634.1147])
-        assert torch.allclose(encoding["target"][0]["area"], expected_area)
+        assert torch.allclose(encoding["labels"][0]["area"], expected_area)
         # verify boxes
         expected_boxes_shape = torch.Size([6, 4])
-        self.assertEqual(encoding["target"][0]["boxes"].shape, expected_boxes_shape)
+        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["target"][0]["boxes"][0], expected_boxes_slice, atol=1e-3)
+        assert 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["target"][0]["image_id"], expected_image_id)
+        assert 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["target"][0]["iscrowd"], expected_is_crowd)
+        assert 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["target"][0]["class_labels"], expected_class_labels)
+        assert torch.allclose(encoding["labels"][0]["class_labels"], expected_class_labels)
         # verify masks
         expected_masks_sum = 822338
-        self.assertEqual(encoding["target"][0]["masks"].sum().item(), expected_masks_sum)
+        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["target"][0]["orig_size"], expected_orig_size)
+        assert torch.allclose(encoding["labels"][0]["orig_size"], expected_orig_size)
         # verify size
         expected_size = torch.tensor([800, 1066])
-        assert torch.allclose(encoding["target"][0]["size"], expected_size)
+        assert torch.allclose(encoding["labels"][0]["size"], expected_size)