Update kwargs validation for preprocess with decorator (#32024)

* BLIP preprocess * BIT preprocess * BRIDGETOWER preprocess * CHAMELEON preprocess * CHINESE_CLIP preprocess * CONVNEXT preprocess * DEIT preprocess * DONUT preprocess * DPT preprocess * FLAVA preprocess * EFFICIENTNET preprocess * FUYU preprocess * GLPN preprocess * IMAGEGPT preprocess * INTRUCTBLIPVIDEO preprocess * VIVIT preprocess * ZOEDEPTH preprocess * VITMATTE preprocess * VIT preprocess * VILT preprocess * VIDEOMAE preprocess * VIDEOLLAVA * TVP processing * TVP fixup * SWIN2SR preprocess * SIGLIP preprocess * SAM preprocess * RT-DETR preprocess * PVT preprocess * POOLFORMER preprocess * PERCEIVER preprocess * OWLVIT preprocess * OWLV2 preprocess * NOUGAT preprocess * MOBILEVIT preprocess * MOBILENETV2 preprocess * MOBILENETV1 preprocess * LEVIT preprocess * LAYOUTLMV2 preprocess * LAYOUTLMV3 preprocess * Add test * Update tests
huggingface · Aug 6, 2024 · fb66ef8 · fb66ef8
1 parent e85d863
commit fb66ef8
Show file tree

Hide file tree

Showing 76 changed files with 189 additions and 826 deletions.
diff --git a/src/transformers/models/bit/image_processing_bit.py b/src/transformers/models/bit/image_processing_bit.py
@@ -36,10 +36,9 @@
     make_list_of_images,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 logger = logging.get_logger(__name__)
@@ -122,23 +121,6 @@ def __init__(
         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.do_convert_rgb = do_convert_rgb
-        self._valid_processor_keys = [
-            "images",
-            "do_resize",
-            "size",
-            "resample",
-            "do_center_crop",
-            "crop_size",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "do_convert_rgb",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     # Copied from transformers.models.clip.image_processing_clip.CLIPImageProcessor.resize
     def resize(
@@ -190,6 +172,7 @@ def resize(
             **kwargs,
         )
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -207,7 +190,6 @@ def preprocess(
         return_tensors: Optional[Union[str, TensorType]] = None,
         data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -274,8 +256,6 @@ def preprocess(
         image_std = image_std if image_std is not None else self.image_std
         do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb
 
-        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
-
         images = make_list_of_images(images)
 
         if not valid_images(images):

diff --git a/src/transformers/models/blip/image_processing_blip.py b/src/transformers/models/blip/image_processing_blip.py
@@ -31,10 +31,9 @@
     make_list_of_images,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 if is_vision_available():
@@ -107,21 +106,6 @@ def __init__(
         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.do_convert_rgb = do_convert_rgb
-        self._valid_processor_keys = [
-            "images",
-            "do_resize",
-            "size",
-            "resample",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "do_convert_rgb",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize with PILImageResampling.BILINEAR->PILImageResampling.BICUBIC
     def resize(
@@ -172,6 +156,7 @@ def resize(
             **kwargs,
         )
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -187,7 +172,6 @@ def preprocess(
         do_convert_rgb: bool = None,
         data_format: ChannelDimension = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -250,8 +234,6 @@ def preprocess(
 
         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, "

diff --git a/src/transformers/models/bridgetower/image_processing_bridgetower.py b/src/transformers/models/bridgetower/image_processing_bridgetower.py
@@ -32,10 +32,9 @@
     is_scaled_image,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 if is_vision_available():
@@ -205,24 +204,6 @@ def __init__(
         self.do_pad = do_pad
         self.do_center_crop = do_center_crop
         self.crop_size = crop_size
-        self._valid_processor_keys = [
-            "images",
-            "do_resize",
-            "size",
-            "size_divisor",
-            "resample",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "do_pad",
-            "do_center_crop",
-            "crop_size",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     # Copied from transformers.models.vilt.image_processing_vilt.ViltImageProcessor.resize
     def resize(
@@ -389,6 +370,7 @@ def pad(
 
         return BatchFeature(data=data, tensor_type=return_tensors)
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -407,7 +389,6 @@ def preprocess(
         return_tensors: Optional[Union[str, TensorType]] = None,
         data_format: ChannelDimension = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -484,8 +465,6 @@ def preprocess(
         size = size if size is not None else self.size
         size = get_size_dict(size, default_to_square=False)
 
-        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
-
         if not is_batched(images):
             images = [images]
 

diff --git a/src/transformers/models/chameleon/image_processing_chameleon.py b/src/transformers/models/chameleon/image_processing_chameleon.py
@@ -33,10 +33,9 @@
     is_valid_image,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 logger = logging.get_logger(__name__)
@@ -141,23 +140,6 @@ def __init__(
         self.image_mean = image_mean if image_mean is not None else [1.0, 1.0, 1.0]
         self.image_std = image_std if image_std is not None else [1.0, 1.0, 1.0]
         self.do_convert_rgb = do_convert_rgb
-        self._valid_processor_keys = [
-            "images",
-            "do_resize",
-            "size",
-            "resample",
-            "do_center_crop",
-            "crop_size",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "do_convert_rgb",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     # Copied from transformers.models.clip.image_processing_clip.CLIPImageProcessor.resize
     def resize(
@@ -209,6 +191,7 @@ def resize(
             **kwargs,
         )
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -226,7 +209,6 @@ def preprocess(
         return_tensors: Optional[Union[str, TensorType]] = None,
         data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -293,8 +275,6 @@ def preprocess(
         image_std = image_std if image_std is not None else self.image_std
         do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb
 
-        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
-
         images = make_batched_images(images)
 
         if not valid_images(images):

diff --git a/src/transformers/models/chinese_clip/image_processing_chinese_clip.py b/src/transformers/models/chinese_clip/image_processing_chinese_clip.py
@@ -36,10 +36,9 @@
     make_list_of_images,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 logger = logging.get_logger(__name__)
@@ -122,23 +121,6 @@ def __init__(
         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.do_convert_rgb = do_convert_rgb
-        self._valid_processor_keys = [
-            "images",
-            "do_resize",
-            "size",
-            "resample",
-            "do_center_crop",
-            "crop_size",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "do_convert_rgb",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     def resize(
         self,
@@ -179,6 +161,7 @@ def resize(
             **kwargs,
         )
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -196,7 +179,6 @@ def preprocess(
         return_tensors: Optional[Union[str, TensorType]] = None,
         data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -265,8 +247,6 @@ def preprocess(
 
         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, "

diff --git a/src/transformers/models/convnext/image_processing_convnext.py b/src/transformers/models/convnext/image_processing_convnext.py
@@ -36,10 +36,9 @@
     make_list_of_images,
     to_numpy_array,
     valid_images,
-    validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, is_vision_available, logging
+from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
 
 
 if is_vision_available():
@@ -114,21 +113,6 @@ def __init__(
         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",
-            "crop_pct",
-            "resample",
-            "do_rescale",
-            "rescale_factor",
-            "do_normalize",
-            "image_mean",
-            "image_std",
-            "return_tensors",
-            "data_format",
-            "input_data_format",
-        ]
 
     def resize(
         self,
@@ -199,6 +183,7 @@ def resize(
                 **kwargs,
             )
 
+    @filter_out_non_signature_kwargs()
     def preprocess(
         self,
         images: ImageInput,
@@ -214,7 +199,6 @@ def preprocess(
         return_tensors: Optional[Union[str, TensorType]] = None,
         data_format: ChannelDimension = ChannelDimension.FIRST,
         input_data_format: Optional[Union[str, ChannelDimension]] = None,
-        **kwargs,
     ) -> PIL.Image.Image:
         """
         Preprocess an image or batch of images.
@@ -276,8 +260,6 @@ def preprocess(
         size = size if size is not None else self.size
         size = get_size_dict(size, default_to_square=False)
 
-        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
-
         images = make_list_of_images(images)
 
         if not valid_images(images):