Skip to content

GitLab

Unverified Commit fb66ef81 authored by Pavel Iakubovskii's avatar Pavel Iakubovskii Committed by GitHub
Browse files

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
parent e85d8639
Hide whitespace changes
Inline Side-by-side
Showing with 55 additions and 396 deletions
src/transformers/models/mobilevit/image_processing_mobilevit.py
View file @ fb66ef81
......@@ -29,10 +29,16 @@ 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
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_torch_available,
is_torch_tensor,
is_vision_available,
logging,
)
if is_vision_available():
......@@ -105,21 +111,6 @@ 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(
......@@ -306,6 +297,7 @@ class MobileViTImageProcessor(BaseImageProcessor):
segmentation_map = segmentation_map.astype(np.int64)
return segmentation_map
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -321,7 +313,6 @@ class MobileViTImageProcessor(BaseImageProcessor):
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.
......@@ -383,8 +374,6 @@ class MobileViTImageProcessor(BaseImageProcessor):
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
View file @ fb66ef81
......@@ -38,10 +38,9 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import TensorType, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
from ...utils.import_utils import is_cv2_available, is_vision_available
......@@ -126,24 +125,6 @@ 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."""
......@@ -375,6 +356,7 @@ class NougatImageProcessor(BaseImageProcessor):
)
return resized_image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -393,7 +375,6 @@ class NougatImageProcessor(BaseImageProcessor):
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.
......@@ -461,8 +442,6 @@ 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/owlv2/image_processing_owlv2.py
View file @ fb66ef81
......@@ -37,11 +37,11 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_scipy_available,
is_torch_available,
is_vision_available,
......@@ -233,20 +233,6 @@ 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,
......@@ -346,6 +332,7 @@ class Owlv2ImageProcessor(BaseImageProcessor):
)
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -360,7 +347,6 @@ class Owlv2ImageProcessor(BaseImageProcessor):
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.
......@@ -416,8 +402,6 @@ 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
View file @ fb66ef81
......@@ -38,10 +38,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_torch_available, logging
if is_torch_available():
......@@ -167,22 +166,6 @@ 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,
......@@ -285,6 +268,7 @@ class OwlViTImageProcessor(BaseImageProcessor):
"""
return rescale(image, rescale_factor, data_format=data_format, input_data_format=input_data_format)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -301,7 +285,6 @@ class OwlViTImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[TensorType, str]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> BatchFeature:
"""
Prepares an image or batch of images for the model.
......@@ -373,7 +356,6 @@ 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
View file @ fb66ef81
......@@ -32,10 +32,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
if is_vision_available():
......@@ -114,22 +113,6 @@ 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,
......@@ -224,6 +207,7 @@ class PerceiverImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -240,7 +224,6 @@ class PerceiverImageProcessor(BaseImageProcessor):
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.
......@@ -303,8 +286,6 @@ 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
View file @ fb66ef81
......@@ -35,10 +35,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
if is_vision_available():
......@@ -133,23 +132,6 @@ 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,
......@@ -227,6 +209,7 @@ class PoolFormerImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -244,7 +227,6 @@ class PoolFormerImageProcessor(BaseImageProcessor):
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.
......@@ -311,8 +293,6 @@ 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
View file @ fb66ef81
......@@ -31,10 +31,9 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import TensorType, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
......@@ -96,20 +95,6 @@ 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(
......@@ -160,6 +145,7 @@ class PvtImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -174,7 +160,6 @@ class PvtImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
):
"""
Preprocess an image or batch of images.
......@@ -233,8 +218,6 @@ 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/rt_detr/image_processing_rt_detr.py
View file @ fb66ef81
......@@ -45,10 +45,10 @@ from ...image_utils import (
to_numpy_array,
valid_images,
validate_annotations,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import (
filter_out_non_signature_kwargs,
is_flax_available,
is_jax_tensor,
is_tf_available,
......@@ -471,27 +471,6 @@ class RTDetrImageProcessor(BaseImageProcessor):
self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD
self.do_pad = do_pad
self.pad_size = pad_size
self._valid_processor_keys = [
"images",
"annotations",
"return_segmentation_masks",
"masks_path",
"do_resize",
"size",
"resample",
"do_rescale",
"rescale_factor",
"do_normalize",
"do_convert_annotations",
"image_mean",
"image_std",
"do_pad",
"pad_size",
"format",
"return_tensors",
"data_format",
"input_data_format",
]
def prepare_annotation(
self,
......@@ -800,6 +779,7 @@ class RTDetrImageProcessor(BaseImageProcessor):
return encoded_inputs
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -821,7 +801,6 @@ class RTDetrImageProcessor(BaseImageProcessor):
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
pad_size: Optional[Dict[str, int]] = None,
**kwargs,
) -> BatchFeature:
"""
Preprocess an image or a batch of images so that it can be used by the model.
......@@ -920,7 +899,6 @@ class RTDetrImageProcessor(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)
# Here, the pad() method pads to the maximum of (width, height). It does not need to be validated.
......
src/transformers/models/sam/image_processing_sam.py
View file @ fb66ef81
......@@ -35,11 +35,11 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_tf_available,
is_torch_available,
is_torchvision_available,
......@@ -162,26 +162,6 @@ 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,
......@@ -409,6 +389,7 @@ class SamImageProcessor(BaseImageProcessor):
return segmentation_map, original_size
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -429,7 +410,6 @@ class SamImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: ChannelDimension = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
):
"""
Preprocess an image or batch of images.
......@@ -513,8 +493,6 @@ 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/siglip/image_processing_siglip.py
View file @ fb66ef81
......@@ -33,10 +33,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
logger = logging.get_logger(__name__)
......@@ -107,22 +106,8 @@ class SiglipImageProcessor(BaseImageProcessor):
self.image_mean = image_mean
self.image_std = image_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",
"return_tensors",
"data_format",
"input_data_format",
"do_convert_rgb",
]
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -138,7 +123,6 @@ class SiglipImageProcessor(BaseImageProcessor):
data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
do_convert_rgb: bool = None,
**kwargs,
) -> PIL.Image.Image:
"""
Preprocess an image or batch of images.
......@@ -199,8 +183,6 @@ 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
View file @ fb66ef81
......@@ -28,10 +28,9 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import TensorType, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
......@@ -66,16 +65,6 @@ 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,
......@@ -118,6 +107,7 @@ class Swin2SRImageProcessor(BaseImageProcessor):
input_data_format=input_data_format,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -128,7 +118,6 @@ class Swin2SRImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
):
"""
Preprocess an image or batch of images.
......@@ -172,8 +161,6 @@ 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/tvp/image_processing_tvp.py
View file @ fb66ef81
......@@ -36,10 +36,9 @@ from ...image_utils import (
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
if is_vision_available():
......@@ -173,27 +172,6 @@ class TvpImageProcessor(BaseImageProcessor):
self.do_flip_channel_order = do_flip_channel_order
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 = [
"videos",
"do_resize",
"size",
"resample",
"do_center_crop",
"crop_size",
"do_rescale",
"rescale_factor",
"do_pad",
"pad_size",
"constant_values",
"pad_mode",
"do_normalize",
"do_flip_channel_order",
"image_mean",
"image_std",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
......@@ -358,6 +336,7 @@ class TvpImageProcessor(BaseImageProcessor):
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
videos: Union[ImageInput, List[ImageInput], List[List[ImageInput]]],
......@@ -379,7 +358,6 @@ class TvpImageProcessor(BaseImageProcessor):
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.
......@@ -459,8 +437,6 @@ class TvpImageProcessor(BaseImageProcessor):
crop_size = crop_size if crop_size is not None else self.crop_size
crop_size = get_size_dict(crop_size, param_name="crop_size")
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
if not valid_images(videos):
raise ValueError(
"Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
......
src/transformers/models/video_llava/image_processing_video_llava.py
View file @ fb66ef81
......@@ -38,10 +38,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
logger = logging.get_logger(__name__)
......@@ -140,24 +139,6 @@ class VideoLlavaImageProcessor(BaseImageProcessor):
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",
"videos",
"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,
......@@ -208,6 +189,7 @@ class VideoLlavaImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: List[ImageInput] = None,
......@@ -226,7 +208,6 @@ class VideoLlavaImageProcessor(BaseImageProcessor):
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.
......@@ -301,8 +282,6 @@ class VideoLlavaImageProcessor(BaseImageProcessor):
if videos is not None:
videos = make_batched_videos(videos)
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
if (videos is not None and not valid_images(videos)) or (images is not None and not valid_images(images)):
raise ValueError(
"Invalid input type. Must be of type PIL.Image.Image, numpy.ndarray, "
......
src/transformers/models/videomae/image_processing_videomae.py
View file @ fb66ef81
......@@ -35,10 +35,9 @@ from ...image_utils import (
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
if is_vision_available():
......@@ -131,22 +130,6 @@ class VideoMAEImageProcessor(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 = [
"videos",
"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,
......@@ -249,6 +232,7 @@ class VideoMAEImageProcessor(BaseImageProcessor):
image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format)
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
videos: ImageInput,
......@@ -265,7 +249,6 @@ class VideoMAEImageProcessor(BaseImageProcessor):
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.
......@@ -328,8 +311,6 @@ class VideoMAEImageProcessor(BaseImageProcessor):
crop_size = crop_size if crop_size is not None else self.crop_size
crop_size = get_size_dict(crop_size, param_name="crop_size")
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
if not valid_images(videos):
raise ValueError(
"Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
......
src/transformers/models/vilt/image_processing_vilt.py
View file @ fb66ef81
......@@ -32,10 +32,9 @@ 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
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
if is_vision_available():
......@@ -192,22 +191,6 @@ class ViltImageProcessor(BaseImageProcessor):
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.do_pad = do_pad
self._valid_processor_keys = [
"images",
"do_resize",
"size",
"size_divisor",
"resample",
"do_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"do_pad",
"return_tensors",
"data_format",
"input_data_format",
]
@classmethod
def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
......@@ -351,6 +334,7 @@ class ViltImageProcessor(BaseImageProcessor):
return BatchFeature(data=data, tensor_type=return_tensors)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -367,7 +351,6 @@ class ViltImageProcessor(BaseImageProcessor):
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.
......@@ -433,8 +416,6 @@ class ViltImageProcessor(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/vit/image_processing_vit.py
View file @ fb66ef81
......@@ -31,10 +31,9 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import TensorType, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
......@@ -96,20 +95,6 @@ class ViTImageProcessor(BaseImageProcessor):
self.rescale_factor = rescale_factor
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_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
......@@ -159,6 +144,7 @@ class ViTImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -173,7 +159,6 @@ class ViTImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
):
"""
Preprocess an image or batch of images.
......@@ -232,8 +217,6 @@ class ViTImageProcessor(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/vitmatte/image_processing_vitmatte.py
View file @ fb66ef81
......@@ -31,10 +31,9 @@ from ...image_utils import (
make_list_of_images,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import TensorType, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
......@@ -88,20 +87,6 @@ class VitMatteImageProcessor(BaseImageProcessor):
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.size_divisibility = size_divisibility
self._valid_processor_keys = [
"images",
"trimaps",
"do_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"do_pad",
"size_divisibility",
"return_tensors",
"data_format",
"input_data_format",
]
def pad_image(
self,
......@@ -144,6 +129,7 @@ class VitMatteImageProcessor(BaseImageProcessor):
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......@@ -158,7 +144,6 @@ class VitMatteImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
):
"""
Preprocess an image or batch of images.
......@@ -213,8 +198,6 @@ class VitMatteImageProcessor(BaseImageProcessor):
images = make_list_of_images(images)
trimaps = make_list_of_images(trimaps, expected_ndims=2)
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
if not valid_images(trimaps):
raise ValueError(
"Invalid trimap type. Must be of type PIL.Image.Image, numpy.ndarray, "
......
src/transformers/models/vivit/image_processing_vivit.py
View file @ fb66ef81
......@@ -39,10 +39,9 @@ from ...image_utils import (
is_valid_image,
to_numpy_array,
valid_images,
validate_kwargs,
validate_preprocess_arguments,
)
from ...utils import logging
from ...utils import filter_out_non_signature_kwargs, logging
if is_vision_available():
......@@ -139,23 +138,6 @@ class VivitImageProcessor(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 = [
"videos",
"do_resize",
"size",
"resample",
"do_center_crop",
"crop_size",
"do_rescale",
"rescale_factor",
"offset",
"do_normalize",
"image_mean",
"image_std",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
......@@ -304,6 +286,7 @@ class VivitImageProcessor(BaseImageProcessor):
image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format)
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
videos: ImageInput,
......@@ -321,7 +304,6 @@ class VivitImageProcessor(BaseImageProcessor):
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.
......@@ -387,8 +369,6 @@ class VivitImageProcessor(BaseImageProcessor):
crop_size = crop_size if crop_size is not None else self.crop_size
crop_size = get_size_dict(crop_size, param_name="crop_size")
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
if not valid_images(videos):
raise ValueError(
"Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
......
src/transformers/models/zoedepth/image_processing_zoedepth.py
View file @ fb66ef81
......@@ -35,7 +35,14 @@ from ...image_utils import (
valid_images,
validate_preprocess_arguments,
)
from ...utils import TensorType, is_torch_available, is_vision_available, logging, requires_backends
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_torch_available,
is_vision_available,
logging,
requires_backends,
)
if is_vision_available():
......@@ -164,24 +171,6 @@ class ZoeDepthImageProcessor(BaseImageProcessor):
self.ensure_multiple_of = ensure_multiple_of
self.resample = resample
self._valid_processor_keys = [
"images",
"do_resize",
"size",
"keep_aspect_ratio",
"ensure_multiple_of",
"resample",
"do_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"do_pad",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
image: np.ndarray,
......@@ -301,6 +290,7 @@ class ZoeDepthImageProcessor(BaseImageProcessor):
input_data_format=input_data_format,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
......
src/transformers/utils/generic.py
View file @ fb66ef81
......@@ -816,6 +816,9 @@ def filter_out_non_signature_kwargs(extra: Optional[list] = None):
is_instance_method = "self" in function_named_args
is_class_method = "cls" in function_named_args
# Mark function as decorated
func._filter_out_non_signature_kwargs = True
@wraps(func)
def wrapper(*args, **kwargs):
valid_kwargs = {}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment