SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update kwargs validation for preprocess with decorator (#32024)

Browse Source 
* 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
This commit is contained in:
Pavel Iakubovskii
2024-08-06 11:33:05 +01:00
committed by GitHub
parent e85d86398a
commit fb66ef8147
76 changed files with 189 additions and 826 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/transformers/models/bit/image_processing_bit.py
View File

@@ -36,10 +36,9 @@ 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__)
@@ -122,23 +121,6 @@ class BitImageProcessor(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",
"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 @@ class BitImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -207,7 +190,6 @@ class BitImageProcessor(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.
@@ -274,8 +256,6 @@ class BitImageProcessor(BaseImageProcessor):
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):

22
src/transformers/models/blip/image_processing_blip.py
View File

@@ -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, 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 @@ class BlipImageProcessor(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",
"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 @@ class BlipImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -187,7 +172,6 @@ class BlipImageProcessor(BaseImageProcessor):
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 @@ class BlipImageProcessor(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, "

25
src/transformers/models/bridgetower/image_processing_bridgetower.py
View File

@@ -32,10 +32,9 @@ from ...image_utils import (
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 @@ class BridgeTowerImageProcessor(BaseImageProcessor):
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 @@ class BridgeTowerImageProcessor(BaseImageProcessor):
return BatchFeature(data=data, tensor_type=return_tensors)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -407,7 +389,6 @@ class BridgeTowerImageProcessor(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.
@@ -484,8 +465,6 @@ class BridgeTowerImageProcessor(BaseImageProcessor):
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]

24
src/transformers/models/chameleon/image_processing_chameleon.py
View File

@@ -33,10 +33,9 @@ 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
logger = logging.get_logger(__name__)
@@ -141,23 +140,6 @@ class ChameleonImageProcessor(BaseImageProcessor):
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 @@ class ChameleonImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -226,7 +209,6 @@ class ChameleonImageProcessor(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.
@@ -293,8 +275,6 @@ class ChameleonImageProcessor(BaseImageProcessor):
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):

24
src/transformers/models/chinese_clip/image_processing_chinese_clip.py
View File

@@ -36,10 +36,9 @@ 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__)
@@ -122,23 +121,6 @@ class ChineseCLIPImageProcessor(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",
"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 @@ class ChineseCLIPImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -196,7 +179,6 @@ class ChineseCLIPImageProcessor(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.
@@ -265,8 +247,6 @@ class ChineseCLIPImageProcessor(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, "

22
src/transformers/models/convnext/image_processing_convnext.py
View File

@@ -36,10 +36,9 @@ 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():
@@ -114,21 +113,6 @@ class ConvNextImageProcessor(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",
"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 @@ class ConvNextImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -214,7 +199,6 @@ class ConvNextImageProcessor(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.
@@ -276,8 +260,6 @@ class ConvNextImageProcessor(BaseImageProcessor):
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):

23
src/transformers/models/deit/image_processing_deit.py
View File

@@ -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, is_vision_available, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
if is_vision_available():
@@ -110,22 +109,6 @@ class DeiTImageProcessor(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.vit.image_processing_vit.ViTImageProcessor.resize with PILImageResampling.BILINEAR->PILImageResampling.BICUBIC
def resize(
@@ -176,6 +159,7 @@ class DeiTImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -192,7 +176,6 @@ class DeiTImageProcessor(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.
@@ -257,8 +240,6 @@ class DeiTImageProcessor(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, "

25
src/transformers/models/donut/image_processing_donut.py
View File

@@ -37,10 +37,9 @@ 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_vision_available
@@ -124,24 +123,6 @@ class DonutImageProcessor(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_thumbnail",
"do_align_long_axis",
"do_pad",
"random_padding",
"do_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"return_tensors",
"data_format",
"input_data_format",
]
def align_long_axis(
self,
@@ -314,6 +295,7 @@ class DonutImageProcessor(BaseImageProcessor):
)
return resized_image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -332,7 +314,6 @@ class DonutImageProcessor(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.
@@ -407,8 +388,6 @@ class DonutImageProcessor(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, "

25
src/transformers/models/dpt/image_processing_dpt.py
View File

@@ -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_torch_available():
@@ -165,24 +164,6 @@ class DPTImageProcessor(BaseImageProcessor):
self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
self.do_pad = do_pad
self.size_divisor = size_divisor
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",
"size_divisor",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
@@ -284,6 +265,7 @@ class DPTImageProcessor(BaseImageProcessor):
return pad(image, ((pad_size_left, pad_size_right), (pad_size_top, pad_size_bottom)), data_format=data_format)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -302,7 +284,6 @@ class DPTImageProcessor(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.
@@ -369,8 +350,6 @@ class DPTImageProcessor(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, "

25
src/transformers/models/efficientnet/image_processing_efficientnet.py
View File

@@ -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, is_vision_available, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, is_vision_available, logging
if is_vision_available():
@@ -119,24 +118,6 @@ class EfficientNetImageProcessor(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.include_top = include_top
self._valid_processor_keys = [
"images",
"do_resize",
"size",
"resample",
"do_center_crop",
"crop_size",
"do_rescale",
"rescale_factor",
"rescale_offset",
"do_normalize",
"image_mean",
"image_std",
"include_top",
"return_tensors",
"data_format",
"input_data_format",
]
# Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize with PILImageResampling.BILINEAR->PILImageResampling.NEAREST
def resize(
@@ -227,6 +208,7 @@ class EfficientNetImageProcessor(BaseImageProcessor):
return rescaled_image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -245,7 +227,6 @@ class EfficientNetImageProcessor(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.
@@ -316,8 +297,6 @@ class EfficientNetImageProcessor(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, "

42
src/transformers/models/flava/image_processing_flava.py
View File

@@ -34,10 +34,9 @@ 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():
@@ -302,41 +301,6 @@ class FlavaImageProcessor(BaseImageProcessor):
self.codebook_image_mean = codebook_image_mean
self.codebook_image_mean = codebook_image_mean if codebook_image_mean is not None else FLAVA_CODEBOOK_MEAN
self.codebook_image_std = codebook_image_std if codebook_image_std is not None else FLAVA_CODEBOOK_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_image_mask",
"input_size_patches",
"total_mask_patches",
"mask_group_min_patches",
"mask_group_max_patches",
"mask_group_min_aspect_ratio",
"mask_group_max_aspect_ratio",
"return_codebook_pixels",
"codebook_do_resize",
"codebook_size",
"codebook_resample",
"codebook_do_center_crop",
"codebook_crop_size",
"codebook_do_rescale",
"codebook_rescale_factor",
"codebook_do_map_pixels",
"codebook_do_normalize",
"codebook_image_mean",
"codebook_image_std",
"return_tensors",
"data_format",
"input_data_format",
]
@classmethod
def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
@@ -486,6 +450,7 @@ class FlavaImageProcessor(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,
images: ImageInput,
@@ -523,7 +488,6 @@ class FlavaImageProcessor(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.
@@ -672,8 +636,6 @@ class FlavaImageProcessor(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, "

20
src/transformers/models/fuyu/image_processing_fuyu.py
View File

@@ -39,6 +39,7 @@ from ...image_utils import (
)
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_torch_available,
is_torch_device,
is_torch_dtype,
@@ -261,24 +262,6 @@ class FuyuImageProcessor(BaseImageProcessor):
self.do_rescale = do_rescale
self.rescale_factor = rescale_factor
self.patch_size = patch_size if patch_size is not None else {"height": 30, "width": 30}
self._valid_processor_keys = [
"images",
"do_resize",
"size",
"resample",
"do_pad",
"padding_value",
"padding_mode",
"do_normalize",
"image_mean",
"image_std",
"do_rescale",
"rescale_factor",
"patch_size",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
@@ -376,6 +359,7 @@ class FuyuImageProcessor(BaseImageProcessor):
)
return padded_image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images,

17
src/transformers/models/glpn/image_processing_glpn.py
View File

@@ -30,10 +30,9 @@ 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__)
@@ -72,16 +71,6 @@ class GLPNImageProcessor(BaseImageProcessor):
self.size_divisor = size_divisor
self.resample = resample
super().__init__(**kwargs)
self._valid_processor_keys = [
"images",
"do_resize",
"size_divisor",
"resample",
"do_rescale",
"return_tensors",
"data_format",
"input_data_format",
]
def resize(
self,
@@ -133,6 +122,7 @@ class GLPNImageProcessor(BaseImageProcessor):
)
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: Union["PIL.Image.Image", TensorType, List["PIL.Image.Image"], List[TensorType]],
@@ -143,7 +133,6 @@ class GLPNImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[TensorType, str]] = None,
data_format: ChannelDimension = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> BatchFeature:
"""
Preprocess the given images.
@@ -187,8 +176,6 @@ class GLPNImageProcessor(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, "

19
src/transformers/models/imagegpt/image_processing_imagegpt.py
View File

@@ -29,10 +29,9 @@ 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():
@@ -103,18 +102,6 @@ class ImageGPTImageProcessor(BaseImageProcessor):
self.resample = resample
self.do_normalize = do_normalize
self.do_color_quantize = do_color_quantize
self._valid_processor_keys = [
"images",
"do_resize",
"size",
"resample",
"do_normalize",
"do_color_quantize",
"clusters",
"return_tensors",
"data_format",
"input_data_format",
]
# Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize
def resize(
@@ -186,6 +173,7 @@ class ImageGPTImageProcessor(BaseImageProcessor):
image = image - 1
return image
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -198,7 +186,6 @@ class ImageGPTImageProcessor(BaseImageProcessor):
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Optional[Union[str, ChannelDimension]] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> PIL.Image.Image:
"""
Preprocess an image or batch of images.
@@ -251,8 +238,6 @@ class ImageGPTImageProcessor(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, "

21
src/transformers/models/instructblipvideo/image_processing_instructblipvideo.py
View File

@@ -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():
@@ -128,21 +127,6 @@ class InstructBlipVideoImageProcessor(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",
"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(
@@ -195,6 +179,7 @@ class InstructBlipVideoImageProcessor(BaseImageProcessor):
)
# Ignore copy
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: VideoInput = None,
@@ -210,7 +195,6 @@ class InstructBlipVideoImageProcessor(BaseImageProcessor):
do_convert_rgb: bool = None,
data_format: ChannelDimension = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> PIL.Image.Image:
"""
Preprocess a video or batch of images/videos.
@@ -272,7 +256,6 @@ class InstructBlipVideoImageProcessor(BaseImageProcessor):
size = get_size_dict(size, default_to_square=False)
videos = make_batched_videos(images)
validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)
validate_preprocess_arguments(
do_rescale=do_rescale,

26
src/transformers/models/layoutlmv2/image_processing_layoutlmv2.py
View File

@@ -28,10 +28,16 @@ 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
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_pytesseract_available,
is_vision_available,
logging,
requires_backends,
)
if is_vision_available():
@@ -138,18 +144,6 @@ 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(
@@ -200,6 +194,7 @@ class LayoutLMv2ImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -212,7 +207,6 @@ class LayoutLMv2ImageProcessor(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.
@@ -257,8 +251,6 @@ 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, "

31
src/transformers/models/layoutlmv3/image_processing_layoutlmv3.py
View File

@@ -31,10 +31,16 @@ 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
from ...utils import (
TensorType,
filter_out_non_signature_kwargs,
is_pytesseract_available,
is_vision_available,
logging,
requires_backends,
)
if is_vision_available():
@@ -165,23 +171,6 @@ 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(
@@ -232,6 +221,7 @@ class LayoutLMv3ImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -249,7 +239,6 @@ class LayoutLMv3ImageProcessor(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.
@@ -316,8 +305,6 @@ 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, "

23
src/transformers/models/levit/image_processing_levit.py
View File

@@ -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, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
@@ -116,22 +115,6 @@ 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,
@@ -188,6 +171,7 @@ class LevitImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -204,7 +188,6 @@ class LevitImageProcessor(BaseImageProcessor):
return_tensors: Optional[TensorType] = None,
data_format: ChannelDimension = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> BatchFeature:
"""
Preprocess an image or batch of images to be used as input to a LeViT model.
@@ -271,8 +254,6 @@ 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, "

23
src/transformers/models/mobilenet_v1/image_processing_mobilenet_v1.py
View File

@@ -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, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
@@ -114,22 +113,6 @@ 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(
@@ -181,6 +164,7 @@ class MobileNetV1ImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -197,7 +181,6 @@ class MobileNetV1ImageProcessor(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.
@@ -262,8 +245,6 @@ 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, "

23
src/transformers/models/mobilenet_v2/image_processing_mobilenet_v2.py
View File

@@ -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_torch_available, is_torch_tensor, logging
from ...utils import TensorType, filter_out_non_signature_kwargs, is_torch_available, is_torch_tensor, logging
if is_torch_available():
@@ -118,22 +117,6 @@ 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(
@@ -185,6 +168,7 @@ class MobileNetV2ImageProcessor(BaseImageProcessor):
**kwargs,
)
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
@@ -201,7 +185,6 @@ class MobileNetV2ImageProcessor(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.
@@ -266,8 +249,6 @@ 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, "

29
src/transformers/models/mobilevit/image_processing_mobilevit.py
View File

@@ -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)

25
src/transformers/models/nougat/image_processing_nougat.py
View File

@@ -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, "

20
src/transformers/models/owlv2/image_processing_owlv2.py
View File

@@ -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, "

22
src/transformers/models/owlvit/image_processing_owlvit.py
View File

@@ -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,

23
src/transformers/models/perceiver/image_processing_perceiver.py
View File

@@ -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, "

24
src/transformers/models/poolformer/image_processing_poolformer.py
View File

@@ -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, "

21
src/transformers/models/pvt/image_processing_pvt.py
View File

@@ -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, "

26
src/transformers/models/rt_detr/image_processing_rt_detr.py
View File

@@ -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.

26
src/transformers/models/sam/image_processing_sam.py
View File

@@ -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, "

22
src/transformers/models/siglip/image_processing_siglip.py
View File

@@ -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, "

17
src/transformers/models/swin2sr/image_processing_swin2sr.py
View File

@@ -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, "

28
src/transformers/models/tvp/image_processing_tvp.py
View File

@@ -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, "

25
src/transformers/models/video_llava/image_processing_video_llava.py
View File

@@ -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, "

23
src/transformers/models/videomae/image_processing_videomae.py
View File

@@ -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, "

23
src/transformers/models/vilt/image_processing_vilt.py
View File

@@ -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, "

21
src/transformers/models/vit/image_processing_vit.py
View File

@@ -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, "

21
src/transformers/models/vitmatte/image_processing_vitmatte.py
View File

@@ -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, "

24
src/transformers/models/vivit/image_processing_vivit.py
View File

@@ -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, "

28
src/transformers/models/zoedepth/image_processing_zoedepth.py
View File

@@ -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,

3
src/transformers/utils/generic.py
View File

@@ -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 = {}

1
tests/models/blip/test_image_processing_blip.py
View File

@@ -43,6 +43,7 @@ class BlipImageProcessingTester(unittest.TestCase):
image_std=[0.26862954, 0.26130258, 0.27577711],
do_convert_rgb=True,
):
super().__init__()
size = size if size is not None else {"height": 20, "width": 20}
self.parent = parent
self.batch_size = batch_size

1
tests/models/bridgetower/test_image_processing_bridgetower.py
View File

@@ -50,6 +50,7 @@ class BridgeTowerImageProcessingTester(unittest.TestCase):
max_resolution=400,
num_channels=3,
):
super().__init__()
self.parent = parent
self.do_resize = do_resize
self.size = size if size is not None else {"shortest_edge": 288}

1
tests/models/chameleon/test_image_processing_chameleon.py
View File

@@ -50,6 +50,7 @@ class ChameleonImageProcessingTester(unittest.TestCase):
image_std=[1.0, 1.0, 1.0],
do_convert_rgb=True,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 18}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/chinese_clip/test_image_processing_chinese_clip.py
View File

@@ -44,6 +44,7 @@ class ChineseCLIPImageProcessingTester(unittest.TestCase):
image_std=[0.26862954, 0.26130258, 0.27577711],
do_convert_rgb=True,
):
super().__init__()
size = size if size is not None else {"height": 224, "width": 224}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/convnext/test_image_processing_convnext.py
View File

@@ -42,6 +42,7 @@ class ConvNextImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
self.parent = parent
self.batch_size = batch_size

1
tests/models/deit/test_image_processing_deit.py
View File

@@ -43,6 +43,7 @@ class DeiTImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 20, "width": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}

1
tests/models/donut/test_image_processing_donut.py
View File

@@ -51,6 +51,7 @@ class DonutImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/dpt/test_image_processing_dpt.py
View File

@@ -43,6 +43,7 @@ class DPTImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/efficientnet/test_image_processing_efficientnet.py
View File

@@ -43,6 +43,7 @@ class EfficientNetImageProcessorTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/flava/test_image_processing_flava.py
View File

@@ -76,6 +76,7 @@ class FlavaImageProcessingTester(unittest.TestCase):
codebook_image_mean=FLAVA_CODEBOOK_MEAN,
codebook_image_std=FLAVA_CODEBOOK_STD,
):
super().__init__()
size = size if size is not None else {"height": 224, "width": 224}
crop_size = crop_size if crop_size is not None else {"height": 224, "width": 224}
codebook_size = codebook_size if codebook_size is not None else {"height": 112, "width": 112}

1
tests/models/glpn/test_image_processing_glpn.py
View File

@@ -46,6 +46,7 @@ class GLPNImageProcessingTester(unittest.TestCase):
size_divisor=32,
do_rescale=True,
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/imagegpt/test_image_processing_imagegpt.py
View File

@@ -51,6 +51,7 @@ class ImageGPTImageProcessingTester(unittest.TestCase):
size=None,
do_normalize=True,
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/instructblipvideo/test_image_processing_instrictblipvideo.py
View File

@@ -50,6 +50,7 @@ class InstructBlipVideoProcessingTester(unittest.TestCase):
do_convert_rgb=True,
frames=4,
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/layoutlmv2/test_image_processing_layoutlmv2.py
View File

@@ -41,6 +41,7 @@ class LayoutLMv2ImageProcessingTester(unittest.TestCase):
size=None,
apply_ocr=True,
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/layoutlmv3/test_image_processing_layoutlmv3.py
View File

@@ -41,6 +41,7 @@ class LayoutLMv3ImageProcessingTester(unittest.TestCase):
size=None,
apply_ocr=True,
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/levit/test_image_processing_levit.py
View File

@@ -43,6 +43,7 @@ class LevitImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"shortest_edge": 18}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/mobilenet_v1/test_image_processing_mobilenet_v1.py
View File

@@ -40,6 +40,7 @@ class MobileNetV1ImageProcessingTester(unittest.TestCase):
do_center_crop=True,
crop_size=None,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/mobilenet_v2/test_image_processing_mobilenet_v2.py
View File

@@ -40,6 +40,7 @@ class MobileNetV2ImageProcessingTester(unittest.TestCase):
do_center_crop=True,
crop_size=None,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/mobilevit/test_image_processing_mobilevit.py
View File

@@ -48,6 +48,7 @@ class MobileViTImageProcessingTester(unittest.TestCase):
crop_size=None,
do_flip_channel_order=True,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/nougat/test_image_processing_nougat.py
View File

@@ -53,6 +53,7 @@ class NougatImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 20, "width": 20}
self.parent = parent
self.batch_size = batch_size

1
tests/models/owlv2/test_image_processing_owlv2.py
View File

@@ -47,6 +47,7 @@ class Owlv2ImageProcessingTester(unittest.TestCase):
image_std=[0.26862954, 0.26130258, 0.27577711],
do_convert_rgb=True,
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/owlvit/test_image_processing_owlvit.py
View File

@@ -44,6 +44,7 @@ class OwlViTImageProcessingTester(unittest.TestCase):
image_std=[0.26862954, 0.26130258, 0.27577711],
do_convert_rgb=True,
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/poolformer/test_image_processing_poolformer.py
View File

@@ -41,6 +41,7 @@ class PoolFormerImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"shortest_edge": 30}
crop_size = crop_size if crop_size is not None else {"height": 30, "width": 30}
self.parent = parent

1
tests/models/pvt/test_image_processing_pvt.py
View File

@@ -41,6 +41,7 @@ class PvtImageProcessingTester(unittest.TestCase):
image_mean=[0.485, 0.456, 0.406],
image_std=[0.229, 0.224, 0.225],
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/rt_detr/test_image_processing_rt_detr.py
View File

@@ -45,6 +45,7 @@ class RTDetrImageProcessingTester(unittest.TestCase):
do_pad=False,
return_tensors="pt",
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/siglip/test_image_processing_siglip.py
View File

@@ -43,6 +43,7 @@ class SiglipImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

1
tests/models/swin2sr/test_image_processing_swin2sr.py
View File

@@ -48,6 +48,7 @@ class Swin2SRImageProcessingTester(unittest.TestCase):
do_pad=True,
pad_size=8,
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels

1
tests/models/tvp/test_image_processing_tvp.py
View File

@@ -58,6 +58,7 @@ class TvpImageProcessingTester(unittest.TestCase):
num_channels=3,
num_frames=2,
):
super().__init__()
self.do_resize = do_resize
self.size = size
self.do_center_crop = do_center_crop

1
tests/models/video_llava/test_image_processing_video_llava.py
View File

@@ -52,6 +52,7 @@ class VideoLlavaImageProcessingTester(unittest.TestCase):
image_std=OPENAI_CLIP_STD,
do_convert_rgb=True,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 20}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}
self.parent = parent

1
tests/models/videomae/test_image_processing_videomae.py
View File

@@ -50,6 +50,7 @@ class VideoMAEImageProcessingTester(unittest.TestCase):
image_std=[0.5, 0.5, 0.5],
crop_size=None,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 18}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}

1
tests/models/vilt/test_image_processing_vilt.py
View File

@@ -46,6 +46,7 @@ class ViltImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"shortest_edge": 30}
self.parent = parent
self.batch_size = batch_size

1
tests/models/vit/test_image_processing_vit.py
View File

@@ -44,6 +44,7 @@ class ViTImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

19
tests/models/vitmatte/test_image_processing_vitmatte.py
View File

@@ -15,6 +15,7 @@
import unittest
import warnings
import numpy as np
@@ -51,6 +52,7 @@ class VitMatteImageProcessingTester(unittest.TestCase):
image_mean=[0.5, 0.5, 0.5],
image_std=[0.5, 0.5, 0.5],
):
super().__init__()
self.parent = parent
self.batch_size = batch_size
self.num_channels = num_channels
@@ -197,3 +199,20 @@ class VitMatteImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
image = np.random.randn(3, 249, 512)
images = image_processing.pad_image(image)
assert images.shape == (3, 256, 512)
def test_image_processor_preprocess_arguments(self):
# vitmatte require additional trimap input for image_processor
# that is why we override original common test
for image_processing_class in self.image_processor_list:
image_processor = image_processing_class(**self.image_processor_dict)
image = self.image_processor_tester.prepare_image_inputs()[0]
trimap = np.random.randint(0, 3, size=image.size[::-1])
with warnings.catch_warnings(record=True) as raised_warnings:
warnings.simplefilter("always")
image_processor(image, trimaps=trimap, extra_argument=True)
messages = " ".join([str(w.message) for w in raised_warnings])
self.assertGreaterEqual(len(raised_warnings), 1)
self.assertIn("extra_argument", messages)

1
tests/models/vivit/test_image_processing_vivit.py
View File

@@ -50,6 +50,7 @@ class VivitImageProcessingTester(unittest.TestCase):
image_std=[0.5, 0.5, 0.5],
crop_size=None,
):
super().__init__()
size = size if size is not None else {"shortest_edge": 18}
crop_size = crop_size if crop_size is not None else {"height": 18, "width": 18}

1
tests/models/zoedepth/test_image_processing_zoedepth.py
View File

@@ -46,6 +46,7 @@ class ZoeDepthImageProcessingTester(unittest.TestCase):
image_std=[0.5, 0.5, 0.5],
do_pad=False,
):
super().__init__()
size = size if size is not None else {"height": 18, "width": 18}
self.parent = parent
self.batch_size = batch_size

27
tests/test_image_processing_common.py
View File

@@ -19,6 +19,7 @@ import os
import pathlib
import tempfile
import time
import warnings
import numpy as np
import requests
@@ -425,8 +426,12 @@ class ImageProcessingTestMixin:
)
def test_image_processor_preprocess_arguments(self):
is_tested = False
for image_processing_class in self.image_processor_list:
image_processor = image_processing_class(**self.image_processor_dict)
# validation done by _valid_processor_keys attribute
if hasattr(image_processor, "_valid_processor_keys") and hasattr(image_processor, "preprocess"):
preprocess_parameter_names = inspect.getfullargspec(image_processor.preprocess).args
preprocess_parameter_names.remove("self")
@@ -434,6 +439,28 @@ class ImageProcessingTestMixin:
valid_processor_keys = image_processor._valid_processor_keys
valid_processor_keys.sort()
self.assertEqual(preprocess_parameter_names, valid_processor_keys)
is_tested = True
# validation done by @filter_out_non_signature_kwargs decorator
if hasattr(image_processor.preprocess, "_filter_out_non_signature_kwargs"):
if hasattr(self.image_processor_tester, "prepare_image_inputs"):
inputs = self.image_processor_tester.prepare_image_inputs()
elif hasattr(self.image_processor_tester, "prepare_video_inputs"):
inputs = self.image_processor_tester.prepare_video_inputs()
else:
self.skipTest(reason="No valid input preparation method found")
with warnings.catch_warnings(record=True) as raised_warnings:
warnings.simplefilter("always")
image_processor(inputs, extra_argument=True)
messages = " ".join([str(w.message) for w in raised_warnings])
self.assertGreaterEqual(len(raised_warnings), 1)
self.assertIn("extra_argument", messages)
is_tested = True
if not is_tested:
self.skipTest(reason="No validation found for `preprocess` method")
class AnnotationFormatTestMixin: