# 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 Perceiver.""" from typing import Optional, Union import numpy as np from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict from ...image_transforms import center_crop, resize, to_channel_dimension_format from ...image_utils import ( IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, ChannelDimension, ImageInput, PILImageResampling, get_image_size, 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, is_vision_available, logging from ...utils.import_utils import requires if is_vision_available(): import PIL logger = logging.get_logger(__name__) @requires(backends=("vision",)) class PerceiverImageProcessor(BaseImageProcessor): r""" Constructs a Perceiver image processor. Args: do_center_crop (`bool`, `optional`, defaults to `True`): Whether or not to center crop the image. If the input size if smaller than `crop_size` along any edge, the image will be padded with zeros and then center cropped. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 256, "width": 256}`): Desired output size when applying center-cropping. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image to `(size["height"], size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Defines the resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the `preprocess` method. 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`): Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize: Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. """ model_input_names = ["pixel_values"] def __init__( self, do_center_crop: bool = True, crop_size: Optional[dict[str, int]] = None, do_resize: bool = True, size: Optional[dict[str, int]] = None, resample: PILImageResampling = PILImageResampling.BICUBIC, do_rescale: bool = True, rescale_factor: Union[int, float] = 1 / 255, do_normalize: bool = True, image_mean: Optional[Union[float, list[float]]] = None, image_std: Optional[Union[float, list[float]]] = None, **kwargs, ) -> None: super().__init__(**kwargs) crop_size = crop_size if crop_size is not None else {"height": 256, "width": 256} crop_size = get_size_dict(crop_size, param_name="crop_size") size = size if size is not None else {"height": 224, "width": 224} size = get_size_dict(size) self.do_center_crop = do_center_crop self.crop_size = crop_size self.do_resize = do_resize self.size = size self.resample = resample self.do_rescale = do_rescale self.rescale_factor = rescale_factor 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 def center_crop( self, image: np.ndarray, crop_size: dict[str, int], size: Optional[int] = None, data_format: Optional[Union[str, ChannelDimension]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, **kwargs, ) -> np.ndarray: """ Center crop an image to `(size["height"] / crop_size["height"] * min_dim, size["width"] / crop_size["width"] * min_dim)`. Where `min_dim = min(size["height"], size["width"])`. If the input size is smaller than `crop_size` along any edge, the image will be padded with zeros and then center cropped. Args: image (`np.ndarray`): Image to center crop. crop_size (`dict[str, int]`): Desired output size after applying the center crop. size (`dict[str, int]`, *optional*): Size of the image after resizing. If not provided, the self.size attribute will be used. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. """ size = self.size if size is None else size size = get_size_dict(size) crop_size = get_size_dict(crop_size, param_name="crop_size") height, width = get_image_size(image, channel_dim=input_data_format) min_dim = min(height, width) cropped_height = (size["height"] / crop_size["height"]) * min_dim cropped_width = (size["width"] / crop_size["width"]) * min_dim return center_crop( image, size=(cropped_height, cropped_width), data_format=data_format, input_data_format=input_data_format, **kwargs, ) # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize with PILImageResampling.BILINEAR->PILImageResampling.BICUBIC def resize( self, image: np.ndarray, size: dict[str, int], resample: PILImageResampling = PILImageResampling.BICUBIC, data_format: Optional[Union[str, ChannelDimension]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, **kwargs, ) -> np.ndarray: """ Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *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. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. 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. Returns: `np.ndarray`: The resized image. """ size = get_size_dict(size) if "height" not in size or "width" not in size: raise ValueError(f"The `size` dictionary must contain the keys `height` and `width`. Got {size.keys()}") output_size = (size["height"], size["width"]) return resize( image, size=output_size, resample=resample, data_format=data_format, input_data_format=input_data_format, **kwargs, ) @filter_out_non_signature_kwargs() def preprocess( self, images: ImageInput, do_center_crop: Optional[bool] = None, crop_size: Optional[dict[str, int]] = None, do_resize: Optional[bool] = None, size: Optional[dict[str, int]] = None, resample: Optional[PILImageResampling] = None, do_rescale: Optional[bool] = None, rescale_factor: Optional[float] = None, do_normalize: Optional[bool] = None, image_mean: Optional[Union[float, list[float]]] = None, image_std: Optional[Union[float, list[float]]] = None, return_tensors: Optional[Union[str, TensorType]] = None, data_format: ChannelDimension = ChannelDimension.FIRST, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> PIL.Image.Image: """ 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_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image to `crop_size`. crop_size (`dict[str, int]`, *optional*, defaults to `self.crop_size`): Desired output size after applying the center crop. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`dict[str, int]`, *optional*, defaults to `self.size`): Size of the image after resizing. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`, Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`): Image mean. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. 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 type `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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. 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_center_crop = do_center_crop if do_center_crop is not None else self.do_center_crop 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") do_resize = do_resize if do_resize is not None else self.do_resize size = size if size is not None else self.size size = get_size_dict(size) resample = resample if resample is not None else self.resample 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_normalize = do_normalize if do_normalize is not None else self.do_normalize image_mean = image_mean if image_mean is not None else self.image_mean image_std = image_std if image_std is not None else self.image_std 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, do_normalize=do_normalize, image_mean=image_mean, image_std=image_std, do_center_crop=do_center_crop, crop_size=crop_size, do_resize=do_resize, size=size, resample=resample, ) # 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_center_crop: images = [ self.center_crop(image, crop_size, size=size, input_data_format=input_data_format) for image in images ] if do_resize: images = [ self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) for image in images ] if do_rescale: images = [ self.rescale(image=image, scale=rescale_factor, input_data_format=input_data_format) for image in images ] if do_normalize: images = [ self.normalize(image=image, mean=image_mean, std=image_std, 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__ = ["PerceiverImageProcessor"]