transformers/src/transformers/models/bagel/image_processing_bagel.py

# coding=utf-8
# Copyright 2025 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 Bagel."""
from typing import Optional, Union

import numpy as np

from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from ...image_transforms import convert_to_rgb, resize, to_channel_dimension_format
from ...image_utils import (
    IMAGENET_STANDARD_MEAN,
    IMAGENET_STANDARD_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,
)


if is_vision_available():
    import PIL


logger = logging.get_logger(__name__)


class BagelImageProcessor(BaseImageProcessor):
    r"""
    Constructs a Bagel image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the
            `do_resize` parameter in the `preprocess` method.
        size (`dict`, *optional*, defaults to `{"height": 384, "width": 384}`):
            Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
            method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. 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`):
            Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be
            overridden by the `rescale_factor` parameter in the `preprocess` method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
            method. 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.
        do_convert_rgb (`bool`, *optional*, defaults to `True`):
            Whether to convert the image to RGB.
    """

    model_input_names = ["pixel_values"]

    def __init__(
        self,
        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,
        do_convert_rgb: Optional[bool] = None,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"height": 384, "width": 384}
        size = get_size_dict(size, default_to_square=True)

        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_STANDARD_MEAN
        self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
        self.do_convert_rgb = do_convert_rgb

        self.background_color = tuple([int(x * 255) for x in self.image_mean])

    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 and pad an image to a square based on the longest edge in `size`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            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`: will be inferred from input
            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.
        """
        if input_data_format is None:
            input_data_format = infer_channel_dimension_format(image)

        height, width = get_image_size(image, input_data_format)
        max_size = max(height, width)

        size = get_size_dict(size, default_to_square=True)
        if size["height"] != size["width"]:
            raise ValueError(
                f"Output height and width must be the same. Got height={size['height']} and width={size['width']}"
            )
        size = size["height"]

        delta = size / max_size
        # Largest side becomes `size` and the other side is scaled according to the aspect ratio.
        output_size_nonpadded = [int(height * delta), int(width * delta)]

        image = resize(
            image,
            size=output_size_nonpadded,
            resample=resample,
            data_format=data_format,
            input_data_format=input_data_format,
            return_numpy=True,
            **kwargs,
        )
        # Expand and pad the images to obtain a square image of dimensions `size x size`
        image = self.pad_to_square(
            image=image,
            input_data_format=input_data_format,
        )
        return image

    @filter_out_non_signature_kwargs()
    def preprocess(
        self,
        images: ImageInput,
        do_resize: Optional[bool] = None,
        size: Optional[dict[str, int]] = None,
        resample: 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,
        do_convert_rgb: Optional[bool] = 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_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`Dict[str, int]`, *optional*, defaults to `self.size`):
                Controls the size of the image after `resize`. The shortest edge of the image is resized to
                `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image
                is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest
                edge equal to `int(size["shortest_edge"] * (1333 / 800))`.
            resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. 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 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_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 to normalize the image by if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to normalize the image by if `do_normalize` is set to `True`.
            do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
                Whether to convert the image to RGB.
            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:
                - `"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_resize = do_resize if do_resize is not None else self.do_resize
        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
        do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb

        size = size if size is not None else self.size
        size = get_size_dict(size, default_to_square=False)
        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_resize=do_resize,
            size=size,
            resample=resample,
        )
        # PIL RGBA images are converted to RGB
        if do_convert_rgb:
            images = [convert_to_rgb(image) for image in images]

        # 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])

        all_images = []
        for image in images:
            if do_resize:
                image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format)
            if do_rescale:
                image = self.rescale(image=image, scale=rescale_factor, input_data_format=input_data_format)
            if do_normalize:
                image = self.normalize(
                    image=image, mean=image_mean, std=image_std, input_data_format=input_data_format
                )

            image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format)
            all_images.append(image)

        data = {"pixel_values": all_images}
        return BatchFeature(data=data, tensor_type=return_tensors)

    def pad_to_square(
        self,
        image: np.ndarray,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> np.array:
        """
        Pads an image to a square based on the longest edge.

        Args:
            image (`np.ndarray`):
                The image to pad.
            data_format (`str` or `ChannelDimension`, *optional*):
                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.
                If unset, will use same as the input image.
            input_data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format for 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.
        """
        height, width = get_image_size(image, input_data_format)
        num_channels = image.shape[0] if input_data_format == ChannelDimension.FIRST else image.shape[-1]

        if height == width:
            image = (
                to_channel_dimension_format(image, data_format, input_data_format)
                if data_format is not None
                else image
            )
            return image

        max_dim = max(height, width)

        if input_data_format == ChannelDimension.FIRST:
            result = np.zeros((num_channels, max_dim, max_dim), dtype=image.dtype)
            for i, color in enumerate(self.background_color):
                result[i, :, :] = color
            if width > height:
                start = (max_dim - height) // 2
                result[:, start : start + height, :] = image
            else:
                start = (max_dim - width) // 2
                result[:, :, start : start + width] = image
        else:
            result = np.zeros((max_dim, max_dim, num_channels), dtype=image.dtype)
            for i, color in enumerate(self.background_color):
                result[:, :, i] = color
            if width > height:
                start = (max_dim - height) // 2
                result[start : start + height, :, :] = image
            else:
                start = (max_dim - width) // 2
                result[:, start : start + width, :] = image

        return result


__all__ = ["BagelImageProcessor"]