Update old existing feature extractor references (#24552)

* Update old existing feature extractor references

* Typo

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* Address comments from review - update 'feature extractor'
Co-authored by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>

src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py

@@ -29,7 +29,7 @@ from detectron2.projects.deeplab import add_deeplab_config
 from PIL import Image
 from torch import Tensor, nn
 
-from transformers.models.maskformer.feature_extraction_maskformer import MaskFormerFeatureExtractor
+from transformers.models.maskformer.feature_extraction_maskformer import MaskFormerImageProcessor
 from transformers.models.maskformer.modeling_maskformer import (
     MaskFormerConfig,
     MaskFormerForInstanceSegmentation,
@@ -164,13 +164,13 @@ class OriginalMaskFormerConfigToOursConverter:
         return config
 
 
-class OriginalMaskFormerConfigToFeatureExtractorConverter:
-    def __call__(self, original_config: object) -> MaskFormerFeatureExtractor:
+class OriginalMaskFormerConfigToImageProcessorConverter:
+    def __call__(self, original_config: object) -> MaskFormerImageProcessor:
         model = original_config.MODEL
         model_input = original_config.INPUT
         dataset_catalog = MetadataCatalog.get(original_config.DATASETS.TEST[0])
 
-        return MaskFormerFeatureExtractor(
+        return MaskFormerImageProcessor(
             image_mean=(torch.tensor(model.PIXEL_MEAN) / 255).tolist(),
             image_std=(torch.tensor(model.PIXEL_STD) / 255).tolist(),
             size=model_input.MIN_SIZE_TEST,
@@ -554,7 +554,7 @@ class OriginalMaskFormerCheckpointToOursConverter:
             yield config, checkpoint
 
 
-def test(original_model, our_model: MaskFormerForInstanceSegmentation, feature_extractor: MaskFormerFeatureExtractor):
+def test(original_model, our_model: MaskFormerForInstanceSegmentation, image_processor: MaskFormerImageProcessor):
     with torch.no_grad():
         original_model = original_model.eval()
         our_model = our_model.eval()
@@ -600,7 +600,7 @@ def test(original_model, our_model: MaskFormerForInstanceSegmentation, feature_e
 
         our_model_out: MaskFormerForInstanceSegmentationOutput = our_model(x)
 
-        our_segmentation = feature_extractor.post_process_segmentation(our_model_out, target_size=(384, 384))
+        our_segmentation = image_processor.post_process_segmentation(our_model_out, target_size=(384, 384))
 
         assert torch.allclose(
             original_segmentation, our_segmentation, atol=1e-3
@@ -686,9 +686,7 @@ if __name__ == "__main__":
     for config_file, checkpoint_file in OriginalMaskFormerCheckpointToOursConverter.using_dirs(
         checkpoints_dir, config_dir
     ):
-        feature_extractor = OriginalMaskFormerConfigToFeatureExtractorConverter()(
-            setup_cfg(Args(config_file=config_file))
-        )
+        image_processor = OriginalMaskFormerConfigToImageProcessorConverter()(setup_cfg(Args(config_file=config_file)))
 
         original_config = setup_cfg(Args(config_file=config_file))
         mask_former_kwargs = OriginalMaskFormer.from_config(original_config)
@@ -712,15 +710,15 @@ if __name__ == "__main__":
             mask_former_for_instance_segmentation
         )
 
-        test(original_model, mask_former_for_instance_segmentation, feature_extractor)
+        test(original_model, mask_former_for_instance_segmentation, image_processor)
 
         model_name = get_name(checkpoint_file)
         logger.info(f"🪄 Saving {model_name}")
 
-        feature_extractor.save_pretrained(save_directory / model_name)
+        image_processor.save_pretrained(save_directory / model_name)
         mask_former_for_instance_segmentation.save_pretrained(save_directory / model_name)
 
-        feature_extractor.push_to_hub(
+        image_processor.push_to_hub(
             repo_path_or_name=save_directory / model_name,
             commit_message="Add model",
             use_temp_dir=True,

src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py

@@ -26,7 +26,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import MaskFormerConfig, MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation, ResNetConfig
+from transformers import MaskFormerConfig, MaskFormerForInstanceSegmentation, MaskFormerImageProcessor, ResNetConfig
 from transformers.utils import logging
 
 
@@ -297,9 +297,9 @@ def convert_maskformer_checkpoint(
     else:
         ignore_index = 255
     reduce_labels = True if "ade" in model_name else False
-    feature_extractor = MaskFormerFeatureExtractor(ignore_index=ignore_index, reduce_labels=reduce_labels)
+    image_processor = MaskFormerImageProcessor(ignore_index=ignore_index, reduce_labels=reduce_labels)
 
-    inputs = feature_extractor(image, return_tensors="pt")
+    inputs = image_processor(image, return_tensors="pt")
 
     outputs = model(**inputs)
 
@@ -340,15 +340,15 @@ def convert_maskformer_checkpoint(
     print("Looks ok!")
 
     if pytorch_dump_folder_path is not None:
-        print(f"Saving model and feature extractor of {model_name} to {pytorch_dump_folder_path}")
+        print(f"Saving model and image processor of {model_name} to {pytorch_dump_folder_path}")
         Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
         model.save_pretrained(pytorch_dump_folder_path)
-        feature_extractor.save_pretrained(pytorch_dump_folder_path)
+        image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
-        print(f"Pushing model and feature extractor of {model_name} to the hub...")
+        print(f"Pushing model and image processor of {model_name} to the hub...")
         model.push_to_hub(f"facebook/{model_name}")
-        feature_extractor.push_to_hub(f"facebook/{model_name}")
+        image_processor.push_to_hub(f"facebook/{model_name}")
 
 
 if __name__ == "__main__":

src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py

@@ -26,7 +26,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import MaskFormerConfig, MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation, SwinConfig
+from transformers import MaskFormerConfig, MaskFormerForInstanceSegmentation, MaskFormerImageProcessor, SwinConfig
 from transformers.utils import logging
 
 
@@ -278,9 +278,9 @@ def convert_maskformer_checkpoint(
     else:
         ignore_index = 255
     reduce_labels = True if "ade" in model_name else False
-    feature_extractor = MaskFormerFeatureExtractor(ignore_index=ignore_index, reduce_labels=reduce_labels)
+    image_processor = MaskFormerImageProcessor(ignore_index=ignore_index, reduce_labels=reduce_labels)
 
-    inputs = feature_extractor(image, return_tensors="pt")
+    inputs = image_processor(image, return_tensors="pt")
 
     outputs = model(**inputs)
 
@@ -294,15 +294,15 @@ def convert_maskformer_checkpoint(
     print("Looks ok!")
 
     if pytorch_dump_folder_path is not None:
-        print(f"Saving model and feature extractor to {pytorch_dump_folder_path}")
+        print(f"Saving model and image processor to {pytorch_dump_folder_path}")
         Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
         model.save_pretrained(pytorch_dump_folder_path)
-        feature_extractor.save_pretrained(pytorch_dump_folder_path)
+        image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
-        print("Pushing model and feature extractor to the hub...")
+        print("Pushing model and image processor to the hub...")
         model.push_to_hub(f"nielsr/{model_name}")
-        feature_extractor.push_to_hub(f"nielsr/{model_name}")
+        image_processor.push_to_hub(f"nielsr/{model_name}")
 
 
 if __name__ == "__main__":

src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py

@@ -27,8 +27,8 @@ from PIL import Image
 
 from transformers import (
     MobileNetV1Config,
-    MobileNetV1FeatureExtractor,
     MobileNetV1ForImageClassification,
+    MobileNetV1ImageProcessor,
     load_tf_weights_in_mobilenet_v1,
 )
 from transformers.utils import logging
@@ -83,12 +83,12 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
     # Load weights from TensorFlow checkpoint
     load_tf_weights_in_mobilenet_v1(model, config, checkpoint_path)
 
-    # Check outputs on an image, prepared by MobileNetV1FeatureExtractor
-    feature_extractor = MobileNetV1FeatureExtractor(
+    # Check outputs on an image, prepared by MobileNetV1ImageProcessor
+    image_processor = MobileNetV1ImageProcessor(
         crop_size={"width": config.image_size, "height": config.image_size},
         size={"shortest_edge": config.image_size + 32},
     )
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     outputs = model(**encoding)
     logits = outputs.logits
 
@@ -107,13 +107,13 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {model_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
         print("Pushing to the hub...")
         repo_id = "google/" + model_name
-        feature_extractor.push_to_hub(repo_id)
+        image_processor.push_to_hub(repo_id)
         model.push_to_hub(repo_id)
 
 

src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py

@@ -99,11 +99,11 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
     load_tf_weights_in_mobilenet_v2(model, config, checkpoint_path)
 
     # Check outputs on an image, prepared by MobileNetV2ImageProcessor
-    feature_extractor = MobileNetV2ImageProcessor(
+    image_processor = MobileNetV2ImageProcessor(
         crop_size={"width": config.image_size, "height": config.image_size},
         size={"shortest_edge": config.image_size + 32},
     )
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     outputs = model(**encoding)
     logits = outputs.logits
 
@@ -143,13 +143,13 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {model_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
         print("Pushing to the hub...")
         repo_id = "google/" + model_name
-        feature_extractor.push_to_hub(repo_id)
+        image_processor.push_to_hub(repo_id)
         model.push_to_hub(repo_id)
 
 

src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py

@@ -26,9 +26,9 @@ from PIL import Image
 
 from transformers import (
     MobileViTConfig,
-    MobileViTFeatureExtractor,
     MobileViTForImageClassification,
     MobileViTForSemanticSegmentation,
+    MobileViTImageProcessor,
 )
 from transformers.utils import logging
 
@@ -211,9 +211,9 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f
     new_state_dict = convert_state_dict(state_dict, model)
     model.load_state_dict(new_state_dict)
 
-    # Check outputs on an image, prepared by MobileViTFeatureExtractor
-    feature_extractor = MobileViTFeatureExtractor(crop_size=config.image_size, size=config.image_size + 32)
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    # Check outputs on an image, prepared by MobileViTImageProcessor
+    image_processor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32)
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     outputs = model(**encoding)
     logits = outputs.logits
 
@@ -265,8 +265,8 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {mobilevit_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
         model_mapping = {
@@ -280,7 +280,7 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f
 
         print("Pushing to the hub...")
         model_name = model_mapping[mobilevit_name]
-        feature_extractor.push_to_hub(model_name, organization="apple")
+        image_processor.push_to_hub(model_name, organization="apple")
         model.push_to_hub(model_name, organization="apple")
 
 

src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.py

@@ -259,8 +259,8 @@ def convert_mobilevitv2_checkpoint(task_name, checkpoint_path, orig_config_path,
     model.load_state_dict(state_dict)
 
     # Check outputs on an image, prepared by MobileViTImageProcessor
-    feature_extractor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32)
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    image_processor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32)
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     outputs = model(**encoding)
 
     # verify classification model
@@ -276,8 +276,8 @@ def convert_mobilevitv2_checkpoint(task_name, checkpoint_path, orig_config_path,
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {task_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
 
 if __name__ == "__main__":

src/transformers/models/owlvit/configuration_owlvit.py

@@ -383,7 +383,7 @@ class OwlViTOnnxConfig(OnnxConfig):
             processor.tokenizer, batch_size=batch_size, seq_length=seq_length, framework=framework
         )
         image_input_dict = super().generate_dummy_inputs(
-            processor.feature_extractor, batch_size=batch_size, framework=framework
+            processor.image_processor, batch_size=batch_size, framework=framework
         )
         return {**text_input_dict, **image_input_dict}
 

src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py

@@ -29,8 +29,8 @@ from huggingface_hub import Repository
 from transformers import (
     CLIPTokenizer,
     OwlViTConfig,
-    OwlViTFeatureExtractor,
     OwlViTForObjectDetection,
+    OwlViTImageProcessor,
     OwlViTModel,
     OwlViTProcessor,
 )
@@ -350,16 +350,16 @@ def convert_owlvit_checkpoint(pt_backbone, flax_params, attn_params, pytorch_dum
     # Save HF model
     hf_model.save_pretrained(repo.local_dir)
 
-    # Initialize feature extractor
-    feature_extractor = OwlViTFeatureExtractor(
+    # Initialize image processor
+    image_processor = OwlViTImageProcessor(
         size=config.vision_config.image_size, crop_size=config.vision_config.image_size
     )
     # Initialize tokenizer
     tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32", pad_token="!", model_max_length=16)
 
     # Initialize processor
-    processor = OwlViTProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
-    feature_extractor.save_pretrained(repo.local_dir)
+    processor = OwlViTProcessor(image_processor=image_processor, tokenizer=tokenizer)
+    image_processor.save_pretrained(repo.local_dir)
     processor.save_pretrained(repo.local_dir)
 
     repo.git_add()

src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py

@@ -29,13 +29,13 @@ from PIL import Image
 
 from transformers import (
     PerceiverConfig,
-    PerceiverFeatureExtractor,
     PerceiverForImageClassificationConvProcessing,
     PerceiverForImageClassificationFourier,
     PerceiverForImageClassificationLearned,
     PerceiverForMaskedLM,
     PerceiverForMultimodalAutoencoding,
     PerceiverForOpticalFlow,
+    PerceiverImageProcessor,
     PerceiverTokenizer,
 )
 from transformers.utils import logging
@@ -389,9 +389,9 @@ def convert_perceiver_checkpoint(pickle_file, pytorch_dump_folder_path, architec
         inputs = encoding.input_ids
         input_mask = encoding.attention_mask
     elif architecture in ["image_classification", "image_classification_fourier", "image_classification_conv"]:
-        feature_extractor = PerceiverFeatureExtractor()
+        image_processor = PerceiverImageProcessor()
         image = prepare_img()
-        encoding = feature_extractor(image, return_tensors="pt")
+        encoding = image_processor(image, return_tensors="pt")
         inputs = encoding.pixel_values
     elif architecture == "optical_flow":
         inputs = torch.randn(1, 2, 27, 368, 496)

src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py

@@ -24,7 +24,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import PoolFormerConfig, PoolFormerFeatureExtractor, PoolFormerForImageClassification
+from transformers import PoolFormerConfig, PoolFormerForImageClassification, PoolFormerImageProcessor
 from transformers.utils import logging
 
 
@@ -141,12 +141,12 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold
     else:
         raise ValueError(f"Size {size} not supported")
 
-    # load feature extractor
-    feature_extractor = PoolFormerFeatureExtractor(crop_pct=crop_pct)
+    # load image processor
+    image_processor = PoolFormerImageProcessor(crop_pct=crop_pct)
 
     # Prepare image
     image = prepare_img()
-    pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
+    pixel_values = image_processor(images=image, return_tensors="pt").pixel_values
 
     logger.info(f"Converting model {model_name}...")
 
@@ -161,9 +161,9 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold
     model.load_state_dict(state_dict)
     model.eval()
 
-    # Define feature extractor
-    feature_extractor = PoolFormerFeatureExtractor(crop_pct=crop_pct)
-    pixel_values = feature_extractor(images=prepare_img(), return_tensors="pt").pixel_values
+    # Define image processor
+    image_processor = PoolFormerImageProcessor(crop_pct=crop_pct)
+    pixel_values = image_processor(images=prepare_img(), return_tensors="pt").pixel_values
 
     # forward pass
     outputs = model(pixel_values)
@@ -187,12 +187,12 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold
     assert logits.shape == expected_shape
     assert torch.allclose(logits[0, :3], expected_slice, atol=1e-2)
 
-    # finally, save model and feature extractor
-    logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...")
+    # finally, save model and image processor
+    logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...")
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     model.save_pretrained(pytorch_dump_folder_path)
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
 
 if __name__ == "__main__":

src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py

@@ -34,7 +34,7 @@ from huggingface_hub import cached_download, hf_hub_url
 from torch import Tensor
 from vissl.models.model_helpers import get_trunk_forward_outputs
 
-from transformers import AutoFeatureExtractor, RegNetConfig, RegNetForImageClassification, RegNetModel
+from transformers import AutoImageProcessor, RegNetConfig, RegNetForImageClassification, RegNetModel
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import logging
 
@@ -262,10 +262,10 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_
         )
         size = 384
         # we can use the convnext one
-        feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size)
-        feature_extractor.push_to_hub(
+        image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size)
+        image_processor.push_to_hub(
             repo_path_or_name=save_directory / model_name,
-            commit_message="Add feature extractor",
+            commit_message="Add image processor",
             output_dir=save_directory / model_name,
         )
 
@@ -294,7 +294,7 @@ if __name__ == "__main__":
         default=True,
         type=bool,
         required=False,
-        help="If True, push model and feature extractor to the hub.",
+        help="If True, push model and image processor to the hub.",
     )
 
     args = parser.parse_args()

src/transformers/models/regnet/convert_regnet_to_pytorch.py

@@ -30,7 +30,7 @@ from huggingface_hub import cached_download, hf_hub_url
 from torch import Tensor
 from vissl.models.model_helpers import get_trunk_forward_outputs
 
-from transformers import AutoFeatureExtractor, RegNetConfig, RegNetForImageClassification, RegNetModel
+from transformers import AutoImageProcessor, RegNetConfig, RegNetForImageClassification, RegNetModel
 from transformers.utils import logging
 
 
@@ -209,10 +209,10 @@ def convert_weight_and_push(
 
         size = 224 if "seer" not in name else 384
         # we can use the convnext one
-        feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size)
-        feature_extractor.push_to_hub(
+        image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size)
+        image_processor.push_to_hub(
             repo_path_or_name=save_directory / name,
-            commit_message="Add feature extractor",
+            commit_message="Add image processor",
             use_temp_dir=True,
         )
 
@@ -449,7 +449,7 @@ if __name__ == "__main__":
         default=True,
         type=bool,
         required=False,
-        help="If True, push model and feature extractor to the hub.",
+        help="If True, push model and image processor to the hub.",
     )
 
     args = parser.parse_args()

src/transformers/models/resnet/convert_resnet_to_pytorch.py

@@ -28,7 +28,7 @@ import torch.nn as nn
 from huggingface_hub import hf_hub_download
 from torch import Tensor
 
-from transformers import AutoFeatureExtractor, ResNetConfig, ResNetForImageClassification
+from transformers import AutoImageProcessor, ResNetConfig, ResNetForImageClassification
 from transformers.utils import logging
 
 
@@ -113,10 +113,10 @@ def convert_weight_and_push(name: str, config: ResNetConfig, save_directory: Pat
         )
 
         # we can use the convnext one
-        feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k")
-        feature_extractor.push_to_hub(
+        image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k")
+        image_processor.push_to_hub(
             repo_path_or_name=save_directory / checkpoint_name,
-            commit_message="Add feature extractor",
+            commit_message="Add image processor",
             use_temp_dir=True,
         )
 
@@ -191,7 +191,7 @@ if __name__ == "__main__":
         default=True,
         type=bool,
         required=False,
-        help="If True, push model and feature extractor to the hub.",
+        help="If True, push model and image processor to the hub.",
     )
 
     args = parser.parse_args()

src/transformers/models/segformer/convert_segformer_original_to_pytorch.py

@@ -27,9 +27,9 @@ from PIL import Image
 
 from transformers import (
     SegformerConfig,
-    SegformerFeatureExtractor,
     SegformerForImageClassification,
     SegformerForSemanticSegmentation,
+    SegformerImageProcessor,
 )
 from transformers.utils import logging
 
@@ -179,14 +179,14 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
     else:
         raise ValueError(f"Size {size} not supported")
 
-    # load feature extractor (only resize + normalize)
-    feature_extractor = SegformerFeatureExtractor(
+    # load image processor (only resize + normalize)
+    image_processor = SegformerImageProcessor(
         image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False
     )
 
     # prepare image
     image = prepare_img()
-    pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
+    pixel_values = image_processor(images=image, return_tensors="pt").pixel_values
 
     logger.info(f"Converting model {model_name}...")
 
@@ -362,11 +362,11 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde
         assert logits.shape == expected_shape
         assert torch.allclose(logits[0, :3, :3, :3], expected_slice, atol=1e-2)
 
-    # finally, save model and feature extractor
-    logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...")
+    # finally, save model and image processor
+    logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...")
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     model.save_pretrained(pytorch_dump_folder_path)
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
 
 if __name__ == "__main__":

src/transformers/models/swin/convert_swin_simmim_to_pytorch.py

@@ -22,7 +22,7 @@ import requests
 import torch
 from PIL import Image
 
-from transformers import SwinConfig, SwinForMaskedImageModeling, ViTFeatureExtractor
+from transformers import SwinConfig, SwinForMaskedImageModeling, ViTImageProcessor
 
 
 def get_swin_config(model_name):
@@ -132,9 +132,9 @@ def convert_swin_checkpoint(model_name, checkpoint_path, pytorch_dump_folder_pat
 
     url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
-    feature_extractor = ViTFeatureExtractor(size={"height": 192, "width": 192})
+    image_processor = ViTImageProcessor(size={"height": 192, "width": 192})
     image = Image.open(requests.get(url, stream=True).raw)
-    inputs = feature_extractor(images=image, return_tensors="pt")
+    inputs = image_processor(images=image, return_tensors="pt")
 
     with torch.no_grad():
         outputs = model(**inputs).logits
@@ -146,13 +146,13 @@ def convert_swin_checkpoint(model_name, checkpoint_path, pytorch_dump_folder_pat
         print(f"Saving model {model_name} to {pytorch_dump_folder_path}")
         model.save_pretrained(pytorch_dump_folder_path)
 
-        print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-        feature_extractor.save_pretrained(pytorch_dump_folder_path)
+        print(f"Saving image processor to {pytorch_dump_folder_path}")
+        image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
-        print(f"Pushing model and feature extractor for {model_name} to hub")
+        print(f"Pushing model and image processor for {model_name} to hub")
         model.push_to_hub(f"microsoft/{model_name}")
-        feature_extractor.push_to_hub(f"microsoft/{model_name}")
+        image_processor.push_to_hub(f"microsoft/{model_name}")
 
 
 if __name__ == "__main__":

src/transformers/models/swin/convert_swin_timm_to_pytorch.py

@@ -7,7 +7,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import AutoFeatureExtractor, SwinConfig, SwinForImageClassification
+from transformers import AutoImageProcessor, SwinConfig, SwinForImageClassification
 
 
 def get_swin_config(swin_name):
@@ -140,9 +140,9 @@ def convert_swin_checkpoint(swin_name, pytorch_dump_folder_path):
 
     url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
-    feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/{}".format(swin_name.replace("_", "-")))
+    image_processor = AutoImageProcessor.from_pretrained("microsoft/{}".format(swin_name.replace("_", "-")))
     image = Image.open(requests.get(url, stream=True).raw)
-    inputs = feature_extractor(images=image, return_tensors="pt")
+    inputs = image_processor(images=image, return_tensors="pt")
 
     timm_outs = timm_model(inputs["pixel_values"])
     hf_outs = model(**inputs).logits
@@ -152,8 +152,8 @@ def convert_swin_checkpoint(swin_name, pytorch_dump_folder_path):
     print(f"Saving model {swin_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
 
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
 
 if __name__ == "__main__":

src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py

@@ -24,7 +24,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import AutoFeatureExtractor, Swinv2Config, Swinv2ForImageClassification
+from transformers import AutoImageProcessor, Swinv2Config, Swinv2ForImageClassification
 
 
 def get_swinv2_config(swinv2_name):
@@ -180,9 +180,9 @@ def convert_swinv2_checkpoint(swinv2_name, pytorch_dump_folder_path):
 
     url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
-    feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/{}".format(swinv2_name.replace("_", "-")))
+    image_processor = AutoImageProcessor.from_pretrained("microsoft/{}".format(swinv2_name.replace("_", "-")))
     image = Image.open(requests.get(url, stream=True).raw)
-    inputs = feature_extractor(images=image, return_tensors="pt")
+    inputs = image_processor(images=image, return_tensors="pt")
 
     timm_outs = timm_model(inputs["pixel_values"])
     hf_outs = model(**inputs).logits
@@ -192,8 +192,8 @@ def convert_swinv2_checkpoint(swinv2_name, pytorch_dump_folder_path):
     print(f"Saving model {swinv2_name} to {pytorch_dump_folder_path}")
     model.save_pretrained(pytorch_dump_folder_path)
 
-    print(f"Saving feature extractor to {pytorch_dump_folder_path}")
-    feature_extractor.save_pretrained(pytorch_dump_folder_path)
+    print(f"Saving image processor to {pytorch_dump_folder_path}")
+    image_processor.save_pretrained(pytorch_dump_folder_path)
 
     model.push_to_hub(
         repo_path_or_name=Path(pytorch_dump_folder_path, swinv2_name),

src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py

@@ -27,7 +27,7 @@ from huggingface_hub import hf_hub_download
 from PIL import Image
 from torchvision.transforms import functional as F
 
-from transformers import DetrFeatureExtractor, TableTransformerConfig, TableTransformerForObjectDetection
+from transformers import DetrImageProcessor, TableTransformerConfig, TableTransformerForObjectDetection
 from transformers.utils import logging
 
 
@@ -242,7 +242,7 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat
         config.id2label = id2label
         config.label2id = {v: k for k, v in id2label.items()}
 
-    feature_extractor = DetrFeatureExtractor(
+    image_processor = DetrImageProcessor(
         format="coco_detection", max_size=800 if "detection" in checkpoint_url else 1000
     )
     model = TableTransformerForObjectDetection(config)
@@ -277,11 +277,11 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat
     print("Looks ok!")
 
     if pytorch_dump_folder_path is not None:
-        # Save model and feature extractor
-        logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...")
+        # Save model and image processor
+        logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...")
         Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
         model.save_pretrained(pytorch_dump_folder_path)
-        feature_extractor.save_pretrained(pytorch_dump_folder_path)
+        image_processor.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub:
         # Push model to HF hub
@@ -292,7 +292,7 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat
             else "microsoft/table-transformer-structure-recognition"
         )
         model.push_to_hub(model_name)
-        feature_extractor.push_to_hub(model_name)
+        image_processor.push_to_hub(model_name)
 
 
 if __name__ == "__main__":

src/transformers/models/timesformer/convert_timesformer_to_pytorch.py

@@ -22,7 +22,7 @@ import numpy as np
 import torch
 from huggingface_hub import hf_hub_download
 
-from transformers import TimesformerConfig, TimesformerForVideoClassification, VideoMAEFeatureExtractor
+from transformers import TimesformerConfig, TimesformerForVideoClassification, VideoMAEImageProcessor
 
 
 def get_timesformer_config(model_name):
@@ -156,9 +156,9 @@ def convert_timesformer_checkpoint(checkpoint_url, pytorch_dump_folder_path, mod
     model.eval()
 
     # verify model on basic input
-    feature_extractor = VideoMAEFeatureExtractor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5])
+    image_processor = VideoMAEImageProcessor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5])
     video = prepare_video()
-    inputs = feature_extractor(video[:8], return_tensors="pt")
+    inputs = image_processor(video[:8], return_tensors="pt")
 
     outputs = model(**inputs)
     logits = outputs.logits
@@ -215,8 +215,8 @@ def convert_timesformer_checkpoint(checkpoint_url, pytorch_dump_folder_path, mod
     print("Logits ok!")
 
     if pytorch_dump_folder_path is not None:
-        print(f"Saving model and feature extractor to {pytorch_dump_folder_path}")
-        feature_extractor.save_pretrained(pytorch_dump_folder_path)
+        print(f"Saving model and image processor to {pytorch_dump_folder_path}")
+        image_processor.save_pretrained(pytorch_dump_folder_path)
         model.save_pretrained(pytorch_dump_folder_path)
 
     if push_to_hub: