# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """Image processor class for Swin2SR.""" from typing import Optional, Union import numpy as np from ...image_processing_utils import BaseImageProcessor, BatchFeature from ...image_transforms import get_image_size, pad, to_channel_dimension_format from ...image_utils import ( ChannelDimension, ImageInput, infer_channel_dimension_format, is_scaled_image, make_flat_list_of_images, to_numpy_array, valid_images, validate_preprocess_arguments, ) from ...utils import TensorType, filter_out_non_signature_kwargs, logging from ...utils.deprecation import deprecate_kwarg logger = logging.get_logger(__name__) class Swin2SRImageProcessor(BaseImageProcessor): r""" Constructs a Swin2SR image processor. Args: do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. """ model_input_names = ["pixel_values"] def __init__( self, do_rescale: bool = True, rescale_factor: Union[int, float] = 1 / 255, do_pad: bool = True, size_divisor: int = 8, **kwargs, ) -> None: super().__init__(**kwargs) self.do_rescale = do_rescale self.rescale_factor = rescale_factor self.do_pad = do_pad pad_size = kwargs.get("pad_size") self.size_divisor = size_divisor if size_divisor is not None else pad_size @property def pad_size(self): logger.warning( "`self.pad_size` attribute is deprecated and will be removed in v5. Use `self.size_divisor` instead", ) return self.size_divisor @pad_size.setter def pad_size(self, value): logger.warning( "`self.pad_size` attribute is deprecated and will be removed in v5. Use `self.size_divisor` instead", ) self.size_divisor = value def pad( self, image: np.ndarray, size: int, data_format: Optional[Union[str, ChannelDimension]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, ): """ Pad an image to make the height and width divisible by `size`. Args: image (`np.ndarray`): Image to pad. size (`int`): The size to make the height and width divisible by. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. Returns: `np.ndarray`: The padded image. """ old_height, old_width = get_image_size(image, input_data_format) pad_height = (old_height // size + 1) * size - old_height pad_width = (old_width // size + 1) * size - old_width return pad( image, ((0, pad_height), (0, pad_width)), mode="symmetric", data_format=data_format, input_data_format=input_data_format, ) @filter_out_non_signature_kwargs() @deprecate_kwarg("pad_size", version="v5", new_name="size_divisor") def preprocess( self, images: ImageInput, do_rescale: Optional[bool] = None, rescale_factor: Optional[float] = None, do_pad: Optional[bool] = None, size_divisor: Optional[int] = None, return_tensors: Optional[Union[str, TensorType]] = None, data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST, input_data_format: Optional[Union[str, ChannelDimension]] = None, ): """ Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to make the height and width divisible by `window_size`. size_divisor (`int`, *optional*, defaults to 32): The size of the sliding window for the local attention. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of typ, input_data_format=input_data_format `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. """ do_rescale = do_rescale if do_rescale is not None else self.do_rescale rescale_factor = rescale_factor if rescale_factor is not None else self.rescale_factor do_pad = do_pad if do_pad is not None else self.do_pad size_divisor = size_divisor if size_divisor is not None else self.size_divisor images = make_flat_list_of_images(images) if not valid_images(images): raise ValueError( "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, " "torch.Tensor, tf.Tensor or jax.ndarray." ) validate_preprocess_arguments( do_rescale=do_rescale, rescale_factor=rescale_factor, ) # All transformations expect numpy arrays. images = [to_numpy_array(image) for image in images] if do_rescale and is_scaled_image(images[0]): logger.warning_once( "It looks like you are trying to rescale already rescaled images. If the input" " images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again." ) if input_data_format is None: # We assume that all images have the same channel dimension format. input_data_format = infer_channel_dimension_format(images[0]) if do_rescale: images = [ self.rescale(image=image, scale=rescale_factor, input_data_format=input_data_format) for image in images ] if do_pad: images = [self.pad(image, size=size_divisor, input_data_format=input_data_format) for image in images] images = [ to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format) for image in images ] data = {"pixel_values": images} return BatchFeature(data=data, tensor_type=return_tensors) __all__ = ["Swin2SRImageProcessor"]