Raise unused kwargs image processor (#29063)

* draft processor arg capture

* add missing vivit model

* add new common test for image preprocess signature

* fix quality

* fix up

* add back missing validations

* quality

* move info level to warning for unused kwargs

src/transformers/models/layoutlmv2/image_processing_layoutlmv2.py

@@ -28,6 +28,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_pytesseract_available, is_vision_available, logging, requires_backends
@@ -137,6 +138,18 @@ class LayoutLMv2ImageProcessor(BaseImageProcessor):
         self.apply_ocr = apply_ocr
         self.ocr_lang = ocr_lang
         self.tesseract_config = tesseract_config
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "apply_ocr",
+            "ocr_lang",
+            "tesseract_config",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize
     def resize(
@@ -244,6 +257,8 @@ class LayoutLMv2ImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/layoutlmv3/image_processing_layoutlmv3.py

@@ -31,6 +31,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_pytesseract_available, is_vision_available, logging, requires_backends
@@ -164,6 +165,23 @@ class LayoutLMv3ImageProcessor(BaseImageProcessor):
         self.apply_ocr = apply_ocr
         self.ocr_lang = ocr_lang
         self.tesseract_config = tesseract_config
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "apply_ocr",
+            "ocr_lang",
+            "tesseract_config",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize
     def resize(
@@ -298,6 +316,8 @@ class LayoutLMv3ImageProcessor(BaseImageProcessor):
         tesseract_config = tesseract_config if tesseract_config is not None else self.tesseract_config
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/levit/image_processing_levit.py

@@ -35,6 +35,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -115,6 +116,22 @@ class LevitImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def resize(
         self,
@@ -254,6 +271,8 @@ class LevitImageProcessor(BaseImageProcessor):
         crop_size = get_size_dict(crop_size, param_name="crop_size")
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/mask2former/image_processing_mask2former.py

@@ -39,6 +39,7 @@ from ...image_utils import (
     is_scaled_image,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import (
@@ -439,6 +440,25 @@ class Mask2FormerImageProcessor(BaseImageProcessor):
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
         self.ignore_index = ignore_index
         self.reduce_labels = reduce_labels
+        self._valid_processor_keys = [
+            "images",
+            "segmentation_maps",
+            "instance_id_to_semantic_id",
+            "do_resize",
+            "size",
+            "size_divisor",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "ignore_index",
+            "reduce_labels",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     @classmethod
     def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
@@ -708,6 +728,8 @@ class Mask2FormerImageProcessor(BaseImageProcessor):
         ignore_index = ignore_index if ignore_index is not None else self.ignore_index
         reduce_labels = reduce_labels if reduce_labels is not None else self.reduce_labels
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/maskformer/image_processing_maskformer.py

@@ -39,6 +39,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import (
@@ -448,6 +449,25 @@ class MaskFormerImageProcessor(BaseImageProcessor):
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
         self.ignore_index = ignore_index
         self.do_reduce_labels = do_reduce_labels
+        self._valid_processor_keys = [
+            "images",
+            "segmentation_maps",
+            "instance_id_to_semantic_id",
+            "do_resize",
+            "size",
+            "size_divisor",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "ignore_index",
+            "do_reduce_labels",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     @classmethod
     def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
@@ -730,6 +750,8 @@ class MaskFormerImageProcessor(BaseImageProcessor):
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                 "torch.Tensor, tf.Tensor or jax.ndarray."
             )
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         validate_preprocess_arguments(
             do_rescale=do_rescale,
             rescale_factor=rescale_factor,

src/transformers/models/mobilenet_v1/image_processing_mobilenet_v1.py

@@ -35,6 +35,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -113,6 +114,22 @@ class MobileNetV1ImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_STANDARD_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.clip.image_processing_clip.CLIPImageProcessor.resize
     def resize(
@@ -245,6 +262,8 @@ class MobileNetV1ImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/mobilenet_v2/image_processing_mobilenet_v2.py

@@ -35,6 +35,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_torch_available, is_torch_tensor, logging
@@ -117,6 +118,22 @@ class MobileNetV2ImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_STANDARD_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.mobilenet_v1.image_processing_mobilenet_v1.MobileNetV1ImageProcessor.resize
     def resize(
@@ -249,6 +266,8 @@ class MobileNetV2ImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/mobilevit/image_processing_mobilevit.py

@@ -29,6 +29,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_torch_available, is_torch_tensor, is_vision_available, logging
@@ -104,6 +105,21 @@ class MobileViTImageProcessor(BaseImageProcessor):
         self.do_center_crop = do_center_crop
         self.crop_size = crop_size
         self.do_flip_channel_order = do_flip_channel_order
+        self._valid_processor_keys = [
+            "images",
+            "segmentation_maps",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_center_crop",
+            "crop_size",
+            "do_flip_channel_order",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.mobilenet_v1.image_processing_mobilenet_v1.MobileNetV1ImageProcessor.resize with PILImageResampling.BICUBIC->PILImageResampling.BILINEAR
     def resize(
@@ -366,6 +382,9 @@ class MobileViTImageProcessor(BaseImageProcessor):
         crop_size = get_size_dict(crop_size, param_name="crop_size")
 
         images = make_list_of_images(images)
+
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if segmentation_maps is not None:
             segmentation_maps = make_list_of_images(segmentation_maps, expected_ndims=2)
 

src/transformers/models/nougat/image_processing_nougat.py

@@ -38,6 +38,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -125,6 +126,24 @@ class NougatImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_crop_margin",
+            "do_resize",
+            "size",
+            "resample",
+            "do_thumbnail",
+            "do_align_long_axis",
+            "do_pad",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def python_find_non_zero(self, image: np.array):
         """This is a reimplementation of a findNonZero function equivalent to cv2."""
@@ -442,6 +461,8 @@ class NougatImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/oneformer/image_processing_oneformer.py

@@ -42,6 +42,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import (
@@ -467,6 +468,25 @@ class OneFormerImageProcessor(BaseImageProcessor):
         self.repo_path = repo_path
         self.metadata = prepare_metadata(load_metadata(repo_path, class_info_file))
         self.num_text = num_text
+        self._valid_processor_keys = [
+            "images",
+            "task_inputs",
+            "segmentation_maps",
+            "instance_id_to_semantic_id",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "ignore_index",
+            "do_reduce_labels",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def resize(
         self,
@@ -714,6 +734,9 @@ class OneFormerImageProcessor(BaseImageProcessor):
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                 "torch.Tensor, tf.Tensor or jax.ndarray."
             )
+
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         validate_preprocess_arguments(
             do_rescale=do_rescale,
             rescale_factor=rescale_factor,

src/transformers/models/owlv2/image_processing_owlv2.py

@@ -37,6 +37,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import (
@@ -232,6 +233,20 @@ class Owlv2ImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else OPENAI_CLIP_MEAN
         self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_pad",
+            "do_resize",
+            "size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def pad(
         self,
@@ -401,6 +416,8 @@ class Owlv2ImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/owlvit/image_processing_owlvit.py

@@ -38,6 +38,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_torch_available, logging
@@ -166,6 +167,22 @@ class OwlViTImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else OPENAI_CLIP_MEAN
         self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def resize(
         self,
@@ -356,6 +373,7 @@ class OwlViTImageProcessor(BaseImageProcessor):
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                 "torch.Tensor, tf.Tensor or jax.ndarray."
             )
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
 
         validate_preprocess_arguments(
             do_rescale=do_rescale,

src/transformers/models/perceiver/image_processing_perceiver.py

@@ -32,6 +32,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_vision_available, logging
@@ -113,6 +114,22 @@ class PerceiverImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_center_crop",
+            "crop_size",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def center_crop(
         self,
@@ -286,6 +303,8 @@ class PerceiverImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/poolformer/image_processing_poolformer.py

@@ -35,6 +35,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_vision_available, logging
@@ -132,6 +133,23 @@ class PoolFormerImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "crop_pct",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def resize(
         self,
@@ -293,6 +311,8 @@ class PoolFormerImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/pvt/image_processing_pvt.py

@@ -31,6 +31,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -95,6 +96,20 @@ class PvtImageProcessor(BaseImageProcessor):
         self.rescale_factor = rescale_factor
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize
     def resize(
@@ -218,6 +233,8 @@ class PvtImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/sam/image_processing_sam.py

@@ -34,6 +34,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import (
@@ -160,6 +161,26 @@ class SamImageProcessor(BaseImageProcessor):
         self.pad_size = pad_size
         self.mask_pad_size = mask_pad_size
         self.do_convert_rgb = do_convert_rgb
+        self._valid_processor_keys = [
+            "images",
+            "segmentation_maps",
+            "do_resize",
+            "size",
+            "mask_size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "do_pad",
+            "pad_size",
+            "mask_pad_size",
+            "do_convert_rgb",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def pad_image(
         self,
@@ -491,6 +512,8 @@ class SamImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/segformer/image_processing_segformer.py

@@ -32,6 +32,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_torch_available, is_torch_tensor, is_vision_available, logging
@@ -118,6 +119,22 @@ class SegformerImageProcessor(BaseImageProcessor):
         self.image_mean = image_mean if image_mean is not None else IMAGENET_DEFAULT_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
         self.do_reduce_labels = do_reduce_labels
+        self._valid_processor_keys = [
+            "images",
+            "segmentation_maps",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "do_reduce_labels",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     @classmethod
     def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
@@ -380,6 +397,9 @@ class SegformerImageProcessor(BaseImageProcessor):
         image_std = image_std if image_std is not None else self.image_std
 
         images = make_list_of_images(images)
+
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if segmentation_maps is not None:
             segmentation_maps = make_list_of_images(segmentation_maps, expected_ndims=2)
 

src/transformers/models/siglip/image_processing_siglip.py

@@ -32,6 +32,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, is_vision_available, logging
@@ -101,6 +102,20 @@ class SiglipImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean
         self.image_std = image_std
+        self._valid_processor_keys = [
+            "images",
+            "do_resize",
+            "size",
+            "resample",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def preprocess(
         self,
@@ -174,6 +189,8 @@ class SiglipImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/swin2sr/image_processing_swin2sr.py

@@ -28,6 +28,7 @@ from ...image_utils import (
     make_list_of_images,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -65,6 +66,16 @@ class Swin2SRImageProcessor(BaseImageProcessor):
         self.rescale_factor = rescale_factor
         self.do_pad = do_pad
         self.pad_size = pad_size
+        self._valid_processor_keys = [
+            "images",
+            "do_rescale",
+            "rescale_factor",
+            "do_pad",
+            "pad_size",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def pad(
         self,
@@ -161,6 +172,8 @@ class Swin2SRImageProcessor(BaseImageProcessor):
 
         images = make_list_of_images(images)
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(images):
             raise ValueError(
                 "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "

src/transformers/models/tvlt/image_processing_tvlt.py

@@ -34,6 +34,7 @@ from ...image_utils import (
     is_valid_image,
     to_numpy_array,
     valid_images,
+    validate_kwargs,
     validate_preprocess_arguments,
 )
 from ...utils import TensorType, logging
@@ -151,6 +152,25 @@ class TvltImageProcessor(BaseImageProcessor):
         self.do_normalize = do_normalize
         self.image_mean = image_mean
         self.image_std = image_std
+        self._valid_processor_keys = [
+            "videos",
+            "do_resize",
+            "size",
+            "patch_size",
+            "num_frames",
+            "resample",
+            "do_center_crop",
+            "crop_size",
+            "do_rescale",
+            "rescale_factor",
+            "do_normalize",
+            "image_mean",
+            "image_std",
+            "is_mixed",
+            "return_tensors",
+            "data_format",
+            "input_data_format",
+        ]
 
     def resize(
         self,
@@ -357,6 +377,8 @@ class TvltImageProcessor(BaseImageProcessor):
         patch_size = patch_size if patch_size is not None else self.patch_size
         num_frames = num_frames if patch_size is not None else self.num_frames
 
+        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
+
         if not valid_images(videos):
             raise ValueError(
                 "Invalid image or video type. Must be of type PIL.Image.Image, numpy.ndarray, "