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/timesformer/modeling_timesformer.py

@@ -513,8 +513,8 @@ TIMESFORMER_START_DOCSTRING = r"""
 TIMESFORMER_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_frames, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See
-            [`VideoMAEFeatureExtractor.__call__`] for details.
+            Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See
+            [`VideoMAEImageProcessor.preprocess`] for details.
 
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned

src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py

@@ -29,7 +29,7 @@ from transformers import (
     TrOCRProcessor,
     VisionEncoderDecoderModel,
     ViTConfig,
-    ViTFeatureExtractor,
+    ViTImageProcessor,
     ViTModel,
 )
 from transformers.utils import logging
@@ -182,9 +182,9 @@ def convert_tr_ocr_checkpoint(checkpoint_url, pytorch_dump_folder_path):
     model.load_state_dict(state_dict)
 
     # Check outputs on an image
-    feature_extractor = ViTFeatureExtractor(size=encoder_config.image_size)
+    image_processor = ViTImageProcessor(size=encoder_config.image_size)
     tokenizer = RobertaTokenizer.from_pretrained("roberta-large")
-    processor = TrOCRProcessor(feature_extractor, tokenizer)
+    processor = TrOCRProcessor(image_processor, tokenizer)
 
     pixel_values = processor(images=prepare_img(checkpoint_url), return_tensors="pt").pixel_values
 

src/transformers/models/van/convert_van_to_pytorch.py

@@ -30,7 +30,7 @@ import torch.nn as nn
 from huggingface_hub import cached_download, hf_hub_download
 from torch import Tensor
 
-from transformers import AutoFeatureExtractor, VanConfig, VanForImageClassification
+from transformers import AutoImageProcessor, VanConfig, VanForImageClassification
 from transformers.models.van.modeling_van import VanLayerScaling
 from transformers.utils import logging
 
@@ -154,10 +154,10 @@ def convert_weight_and_push(
         )
 
         # 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,
         )
 
@@ -277,7 +277,7 @@ 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/videomae/convert_videomae_to_pytorch.py

@@ -24,9 +24,9 @@ from huggingface_hub import hf_hub_download
 
 from transformers import (
     VideoMAEConfig,
-    VideoMAEFeatureExtractor,
     VideoMAEForPreTraining,
     VideoMAEForVideoClassification,
+    VideoMAEImageProcessor,
 )
 
 
@@ -198,9 +198,9 @@ def convert_videomae_checkpoint(checkpoint_url, pytorch_dump_folder_path, model_
     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, return_tensors="pt")
+    inputs = image_processor(video, return_tensors="pt")
 
     if "finetuned" not in model_name:
         local_path = hf_hub_download(repo_id="hf-internal-testing/bool-masked-pos", filename="bool_masked_pos.pt")
@@ -288,8 +288,8 @@ def convert_videomae_checkpoint(checkpoint_url, pytorch_dump_folder_path, model_
         print("Loss 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:

src/transformers/models/vilt/convert_vilt_original_to_pytorch.py

@@ -27,11 +27,11 @@ from PIL import Image
 from transformers import (
     BertTokenizer,
     ViltConfig,
-    ViltFeatureExtractor,
     ViltForImageAndTextRetrieval,
     ViltForImagesAndTextClassification,
     ViltForMaskedLM,
     ViltForQuestionAnswering,
+    ViltImageProcessor,
     ViltProcessor,
 )
 from transformers.utils import logging
@@ -223,9 +223,9 @@ def convert_vilt_checkpoint(checkpoint_url, pytorch_dump_folder_path):
         model.load_state_dict(state_dict)
 
     # Define processor
-    feature_extractor = ViltFeatureExtractor(size=384)
+    image_processor = ViltImageProcessor(size=384)
     tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
-    processor = ViltProcessor(feature_extractor, tokenizer)
+    processor = ViltProcessor(image_processor, tokenizer)
 
     # Forward pass on example inputs (image + text)
     if nlvr_model:

src/transformers/models/vit/convert_dino_to_pytorch.py

@@ -24,7 +24,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import ViTConfig, ViTFeatureExtractor, ViTForImageClassification, ViTModel
+from transformers import ViTConfig, ViTForImageClassification, ViTImageProcessor, ViTModel
 from transformers.utils import logging
 
 
@@ -175,9 +175,9 @@ def convert_vit_checkpoint(model_name, pytorch_dump_folder_path, base_model=True
         model = ViTForImageClassification(config).eval()
     model.load_state_dict(state_dict)
 
-    # Check outputs on an image, prepared by ViTFeatureExtractor
-    feature_extractor = ViTFeatureExtractor()
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    # Check outputs on an image, prepared by ViTImageProcessor
+    image_processor = ViTImageProcessor()
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     pixel_values = encoding["pixel_values"]
     outputs = model(pixel_values)
 
@@ -192,8 +192,8 @@ def convert_vit_checkpoint(model_name, pytorch_dump_folder_path, base_model=True
     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 __name__ == "__main__":

src/transformers/models/vit/convert_vit_timm_to_pytorch.py

@@ -25,7 +25,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import DeiTFeatureExtractor, ViTConfig, ViTFeatureExtractor, ViTForImageClassification, ViTModel
+from transformers import DeiTImageProcessor, ViTConfig, ViTForImageClassification, ViTImageProcessor, ViTModel
 from transformers.utils import logging
 
 
@@ -208,12 +208,12 @@ def convert_vit_checkpoint(vit_name, pytorch_dump_folder_path):
         model = ViTForImageClassification(config).eval()
     model.load_state_dict(state_dict)
 
-    # Check outputs on an image, prepared by ViTFeatureExtractor/DeiTFeatureExtractor
+    # Check outputs on an image, prepared by ViTImageProcessor/DeiTImageProcessor
     if "deit" in vit_name:
-        feature_extractor = DeiTFeatureExtractor(size=config.image_size)
+        image_processor = DeiTImageProcessor(size=config.image_size)
     else:
-        feature_extractor = ViTFeatureExtractor(size=config.image_size)
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+        image_processor = ViTImageProcessor(size=config.image_size)
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     pixel_values = encoding["pixel_values"]
     outputs = model(pixel_values)
 
@@ -229,8 +229,8 @@ def convert_vit_checkpoint(vit_name, pytorch_dump_folder_path):
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {vit_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/vit_mae/convert_vit_mae_to_pytorch.py

@@ -20,7 +20,7 @@ import requests
 import torch
 from PIL import Image
 
-from transformers import ViTMAEConfig, ViTMAEFeatureExtractor, ViTMAEForPreTraining
+from transformers import ViTMAEConfig, ViTMAEForPreTraining, ViTMAEImageProcessor
 
 
 def rename_key(name):
@@ -120,7 +120,7 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path):
 
     state_dict = torch.hub.load_state_dict_from_url(checkpoint_url, map_location="cpu")["model"]
 
-    feature_extractor = ViTMAEFeatureExtractor(size=config.image_size)
+    image_processor = ViTMAEImageProcessor(size=config.image_size)
 
     new_state_dict = convert_state_dict(state_dict, config)
 
@@ -130,8 +130,8 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path):
     url = "https://user-images.githubusercontent.com/11435359/147738734-196fd92f-9260-48d5-ba7e-bf103d29364d.jpg"
 
     image = Image.open(requests.get(url, stream=True).raw)
-    feature_extractor = ViTMAEFeatureExtractor(size=config.image_size)
-    inputs = feature_extractor(images=image, return_tensors="pt")
+    image_processor = ViTMAEImageProcessor(size=config.image_size)
+    inputs = image_processor(images=image, return_tensors="pt")
 
     # forward pass
     torch.manual_seed(2)
@@ -157,8 +157,8 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path):
     print(f"Saving model 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/vit_msn/convert_msn_to_pytorch.py

@@ -22,7 +22,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import ViTFeatureExtractor, ViTMSNConfig, ViTMSNModel
+from transformers import ViTImageProcessor, ViTMSNConfig, ViTMSNModel
 from transformers.image_utils import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
 
 
@@ -180,7 +180,7 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path):
 
     state_dict = torch.hub.load_state_dict_from_url(checkpoint_url, map_location="cpu")["target_encoder"]
 
-    feature_extractor = ViTFeatureExtractor(size=config.image_size)
+    image_processor = ViTImageProcessor(size=config.image_size)
 
     remove_projection_head(state_dict)
     rename_keys = create_rename_keys(config, base_model=True)
@@ -195,10 +195,10 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path):
     url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
     image = Image.open(requests.get(url, stream=True).raw)
-    feature_extractor = ViTFeatureExtractor(
+    image_processor = ViTImageProcessor(
         size=config.image_size, image_mean=IMAGENET_DEFAULT_MEAN, image_std=IMAGENET_DEFAULT_STD
     )
-    inputs = feature_extractor(images=image, return_tensors="pt")
+    inputs = image_processor(images=image, return_tensors="pt")
 
     # forward pass
     torch.manual_seed(2)
@@ -224,8 +224,8 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path):
     print(f"Saving model 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/x_clip/convert_x_clip_original_pytorch_to_hf.py

@@ -23,7 +23,7 @@ from huggingface_hub import hf_hub_download
 from transformers import (
     CLIPTokenizer,
     CLIPTokenizerFast,
-    VideoMAEFeatureExtractor,
+    VideoMAEImageProcessor,
     XCLIPConfig,
     XCLIPModel,
     XCLIPProcessor,
@@ -291,10 +291,10 @@ def convert_xclip_checkpoint(model_name, pytorch_dump_folder_path=None, push_to_
     model.eval()
 
     size = 336 if model_name == "xclip-large-patch14-16-frames" else 224
-    feature_extractor = VideoMAEFeatureExtractor(size=size)
+    image_processor = VideoMAEImageProcessor(size=size)
     slow_tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
     fast_tokenizer = CLIPTokenizerFast.from_pretrained("openai/clip-vit-base-patch32")
-    processor = XCLIPProcessor(feature_extractor=feature_extractor, tokenizer=fast_tokenizer)
+    processor = XCLIPProcessor(image_processor=image_processor, tokenizer=fast_tokenizer)
 
     video = prepare_video(num_frames)
     inputs = processor(

src/transformers/models/yolos/convert_yolos_to_pytorch.py

@@ -24,7 +24,7 @@ import torch
 from huggingface_hub import hf_hub_download
 from PIL import Image
 
-from transformers import YolosConfig, YolosFeatureExtractor, YolosForObjectDetection
+from transformers import YolosConfig, YolosForObjectDetection, YolosImageProcessor
 from transformers.utils import logging
 
 
@@ -172,10 +172,10 @@ def convert_yolos_checkpoint(
     new_state_dict = convert_state_dict(state_dict, model)
     model.load_state_dict(new_state_dict)
 
-    # Check outputs on an image, prepared by YolosFeatureExtractor
+    # Check outputs on an image, prepared by YolosImageProcessor
     size = 800 if yolos_name != "yolos_ti" else 512
-    feature_extractor = YolosFeatureExtractor(format="coco_detection", size=size)
-    encoding = feature_extractor(images=prepare_img(), return_tensors="pt")
+    image_processor = YolosImageProcessor(format="coco_detection", size=size)
+    encoding = image_processor(images=prepare_img(), return_tensors="pt")
     outputs = model(**encoding)
     logits, pred_boxes = outputs.logits, outputs.pred_boxes
 
@@ -224,8 +224,8 @@ def convert_yolos_checkpoint(
     Path(pytorch_dump_folder_path).mkdir(exist_ok=True)
     print(f"Saving model {yolos_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 = {
@@ -238,7 +238,7 @@ def convert_yolos_checkpoint(
 
         print("Pushing to the hub...")
         model_name = model_mapping[yolos_name]
-        feature_extractor.push_to_hub(model_name, organization="hustvl")
+        image_processor.push_to_hub(model_name, organization="hustvl")
         model.push_to_hub(model_name, organization="hustvl")
 
 

src/transformers/onnx/__main__.py

@@ -19,7 +19,7 @@ from pathlib import Path
 
 from packaging import version
 
-from .. import AutoFeatureExtractor, AutoProcessor, AutoTokenizer
+from .. import AutoFeatureExtractor, AutoImageProcessor, AutoProcessor, AutoTokenizer
 from ..utils import logging
 from ..utils.import_utils import is_optimum_available
 from .convert import export, validate_model_outputs
@@ -145,6 +145,8 @@ def export_with_transformers(args):
             preprocessor = get_preprocessor(args.model)
         elif args.preprocessor == "tokenizer":
             preprocessor = AutoTokenizer.from_pretrained(args.model)
+        elif args.preprocessor == "image_processor":
+            preprocessor = AutoImageProcessor.from_pretrained(args.model)
         elif args.preprocessor == "feature_extractor":
             preprocessor = AutoFeatureExtractor.from_pretrained(args.model)
         elif args.preprocessor == "processor":
@@ -213,7 +215,7 @@ def main():
     parser.add_argument(
         "--preprocessor",
         type=str,
-        choices=["auto", "tokenizer", "feature_extractor", "processor"],
+        choices=["auto", "tokenizer", "feature_extractor", "image_processor", "processor"],
         default="auto",
         help="Which type of preprocessor to use. 'auto' tries to automatically detect it.",
     )

tests/models/beit/test_modeling_beit.py

@@ -49,7 +49,7 @@ if is_vision_available():
     import PIL
     from PIL import Image
 
-    from transformers import BeitFeatureExtractor
+    from transformers import BeitImageProcessor
 
 
 class BeitModelTester:
@@ -342,18 +342,16 @@ def prepare_img():
 @require_vision
 class BeitModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
-        return (
-            BeitFeatureExtractor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None
-        )
+    def default_image_processor(self):
+        return BeitImageProcessor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None
 
     @slow
     def test_inference_masked_image_modeling_head(self):
         model = BeitForMaskedImageModeling.from_pretrained("microsoft/beit-base-patch16-224-pt22k").to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values.to(torch_device)
+        pixel_values = image_processor(images=image, return_tensors="pt").pixel_values.to(torch_device)
 
         # prepare bool_masked_pos
         bool_masked_pos = torch.ones((1, 196), dtype=torch.bool).to(torch_device)
@@ -377,9 +375,9 @@ class BeitModelIntegrationTest(unittest.TestCase):
     def test_inference_image_classification_head_imagenet_1k(self):
         model = BeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224").to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():
@@ -403,9 +401,9 @@ class BeitModelIntegrationTest(unittest.TestCase):
             torch_device
         )
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():
@@ -428,11 +426,11 @@ class BeitModelIntegrationTest(unittest.TestCase):
         model = BeitForSemanticSegmentation.from_pretrained("microsoft/beit-base-finetuned-ade-640-640")
         model = model.to(torch_device)
 
-        feature_extractor = BeitFeatureExtractor(do_resize=True, size=640, do_center_crop=False)
+        image_processor = BeitImageProcessor(do_resize=True, size=640, do_center_crop=False)
 
         ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test")
         image = Image.open(ds[0]["file"])
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():
@@ -471,11 +469,11 @@ class BeitModelIntegrationTest(unittest.TestCase):
         model = BeitForSemanticSegmentation.from_pretrained("microsoft/beit-base-finetuned-ade-640-640")
         model = model.to(torch_device)
 
-        feature_extractor = BeitFeatureExtractor(do_resize=True, size=640, do_center_crop=False)
+        image_processor = BeitImageProcessor(do_resize=True, size=640, do_center_crop=False)
 
         ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test")
         image = Image.open(ds[0]["file"])
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():
@@ -483,10 +481,10 @@ class BeitModelIntegrationTest(unittest.TestCase):
 
         outputs.logits = outputs.logits.detach().cpu()
 
-        segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)])
+        segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)])
         expected_shape = torch.Size((500, 300))
         self.assertEqual(segmentation[0].shape, expected_shape)
 
-        segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs)
+        segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs)
         expected_shape = torch.Size((160, 160))
         self.assertEqual(segmentation[0].shape, expected_shape)

tests/models/beit/test_modeling_flax_beit.py

@@ -33,7 +33,7 @@ if is_flax_available():
 if is_vision_available():
     from PIL import Image
 
-    from transformers import BeitFeatureExtractor
+    from transformers import BeitImageProcessor
 
 
 class FlaxBeitModelTester(unittest.TestCase):
@@ -219,18 +219,16 @@ def prepare_img():
 @require_flax
 class FlaxBeitModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
-        return (
-            BeitFeatureExtractor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None
-        )
+    def default_image_processor(self):
+        return BeitImageProcessor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None
 
     @slow
     def test_inference_masked_image_modeling_head(self):
         model = FlaxBeitForMaskedImageModeling.from_pretrained("microsoft/beit-base-patch16-224-pt22k")
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values
+        pixel_values = image_processor(images=image, return_tensors="np").pixel_values
 
         # prepare bool_masked_pos
         bool_masked_pos = np.ones((1, 196), dtype=bool)
@@ -253,9 +251,9 @@ class FlaxBeitModelIntegrationTest(unittest.TestCase):
     def test_inference_image_classification_head_imagenet_1k(self):
         model = FlaxBeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224")
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="np")
+        inputs = image_processor(images=image, return_tensors="np")
 
         # forward pass
         outputs = model(**inputs)
@@ -276,9 +274,9 @@ class FlaxBeitModelIntegrationTest(unittest.TestCase):
     def test_inference_image_classification_head_imagenet_22k(self):
         model = FlaxBeitForImageClassification.from_pretrained("microsoft/beit-large-patch16-224-pt22k-ft22k")
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="np")
+        inputs = image_processor(images=image, return_tensors="np")
 
         # forward pass
         outputs = model(**inputs)

tests/models/bit/test_modeling_bit.py

@@ -297,7 +297,7 @@ def prepare_img():
 @require_vision
 class BitModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
+    def default_image_processor(self):
         return (
             BitImageProcessor.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None
         )
@@ -306,9 +306,9 @@ class BitModelIntegrationTest(unittest.TestCase):
     def test_inference_image_classification_head(self):
         model = BitForImageClassification.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():

tests/models/bridgetower/test_image_processing_bridgetower.py

@@ -145,7 +145,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te
         pass
 
     def test_call_pil(self):
-        # Initialize feature_extractor
+        # Initialize image processor
         image_processing = self.image_processing_class(**self.image_processor_dict)
         # create random PIL images
         image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False)
@@ -176,7 +176,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te
         )
 
     def test_call_numpy(self):
-        # Initialize feature_extractor
+        # Initialize image processor
         image_processing = self.image_processing_class(**self.image_processor_dict)
         # create random numpy tensors
         image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, numpify=True)
@@ -207,7 +207,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te
         )
 
     def test_call_pytorch(self):
-        # Initialize feature_extractor
+        # Initialize image processor
         image_processing = self.image_processing_class(**self.image_processor_dict)
         # create random PyTorch tensors
         image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, torchify=True)
@@ -238,7 +238,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te
         )
 
     def test_equivalence_pad_and_create_pixel_mask(self):
-        # Initialize feature_extractors
+        # Initialize image processors
         image_processing_1 = self.image_processing_class(**self.image_processor_dict)
         image_processing_2 = self.image_processing_class(do_resize=False, do_normalize=False, do_rescale=False)
         # create random PyTorch tensors

tests/models/conditional_detr/test_modeling_conditional_detr.py

@@ -43,7 +43,7 @@ if is_timm_available():
 if is_vision_available():
     from PIL import Image
 
-    from transformers import ConditionalDetrFeatureExtractor
+    from transformers import ConditionalDetrImageProcessor
 
 
 class ConditionalDetrModelTester:
@@ -493,9 +493,9 @@ def prepare_img():
 @slow
 class ConditionalDetrModelIntegrationTests(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
+    def default_image_processor(self):
         return (
-            ConditionalDetrFeatureExtractor.from_pretrained("microsoft/conditional-detr-resnet-50")
+            ConditionalDetrImageProcessor.from_pretrained("microsoft/conditional-detr-resnet-50")
             if is_vision_available()
             else None
         )
@@ -503,9 +503,9 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase):
     def test_inference_no_head(self):
         model = ConditionalDetrModel.from_pretrained("microsoft/conditional-detr-resnet-50").to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        encoding = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         with torch.no_grad():
             outputs = model(**encoding)
@@ -522,9 +522,9 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase):
             torch_device
         )
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        encoding = image_processor(images=image, return_tensors="pt").to(torch_device)
         pixel_values = encoding["pixel_values"].to(torch_device)
         pixel_mask = encoding["pixel_mask"].to(torch_device)
 
@@ -547,7 +547,7 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase):
         self.assertTrue(torch.allclose(outputs.pred_boxes[0, :3, :3], expected_slice_boxes, atol=1e-4))
 
         # verify postprocessing
-        results = feature_extractor.post_process_object_detection(
+        results = image_processor.post_process_object_detection(
             outputs, threshold=0.3, target_sizes=[image.size[::-1]]
         )[0]
         expected_scores = torch.tensor([0.8330, 0.8313, 0.8039, 0.6829, 0.5355]).to(torch_device)

tests/models/convnext/test_modeling_convnext.py

@@ -38,7 +38,7 @@ if is_torch_available():
 if is_vision_available():
     from PIL import Image
 
-    from transformers import AutoFeatureExtractor
+    from transformers import AutoImageProcessor
 
 
 class ConvNextModelTester:
@@ -285,16 +285,16 @@ def prepare_img():
 @require_vision
 class ConvNextModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
-        return AutoFeatureExtractor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None
+    def default_image_processor(self):
+        return AutoImageProcessor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None
 
     @slow
     def test_inference_image_classification_head(self):
         model = ConvNextForImageClassification.from_pretrained("facebook/convnext-tiny-224").to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():

tests/models/convnext/test_modeling_tf_convnext.py

@@ -38,7 +38,7 @@ if is_tf_available():
 if is_vision_available():
     from PIL import Image
 
-    from transformers import ConvNextFeatureExtractor
+    from transformers import ConvNextImageProcessor
 
 
 class TFConvNextModelTester:
@@ -279,18 +279,16 @@ def prepare_img():
 @require_vision
 class TFConvNextModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
-        return (
-            ConvNextFeatureExtractor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None
-        )
+    def default_image_processor(self):
+        return ConvNextImageProcessor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None
 
     @slow
     def test_inference_image_classification_head(self):
         model = TFConvNextForImageClassification.from_pretrained("facebook/convnext-tiny-224")
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="tf")
+        inputs = image_processor(images=image, return_tensors="tf")
 
         # forward pass
         outputs = model(**inputs)

tests/models/cvt/test_modeling_cvt.py

@@ -38,7 +38,7 @@ if is_torch_available():
 if is_vision_available():
     from PIL import Image
 
-    from transformers import AutoFeatureExtractor
+    from transformers import AutoImageProcessor
 
 
 class CvtConfigTester(ConfigTester):
@@ -264,16 +264,16 @@ def prepare_img():
 @require_vision
 class CvtModelIntegrationTest(unittest.TestCase):
     @cached_property
-    def default_feature_extractor(self):
-        return AutoFeatureExtractor.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0])
+    def default_image_processor(self):
+        return AutoImageProcessor.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0])
 
     @slow
     def test_inference_image_classification_head(self):
         model = CvtForImageClassification.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device)
 
-        feature_extractor = self.default_feature_extractor
+        image_processor = self.default_image_processor
         image = prepare_img()
-        inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device)
+        inputs = image_processor(images=image, return_tensors="pt").to(torch_device)
 
         # forward pass
         with torch.no_grad():