Wan2.1/models/hyvideo/text_encoder/llava/image_processing_llava.py

# coding=utf-8
# Copyright 2024 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 LLaVa."""

from typing import Dict, List, Optional, Tuple, Union

import numpy as np

from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from ...image_transforms import (
    convert_to_rgb,
    get_resize_output_image_size,
    resize,
    to_channel_dimension_format,
)
from ...image_utils import (
    OPENAI_CLIP_MEAN,
    OPENAI_CLIP_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    get_image_size,
    infer_channel_dimension_format,
    is_scaled_image,
    make_list_of_images,
    to_numpy_array,
    valid_images,
    validate_kwargs,
    validate_preprocess_arguments,
)
from ...utils import TensorType, is_vision_available, logging


logger = logging.get_logger(__name__)


if is_vision_available():
    import PIL


class LlavaImageProcessor(BaseImageProcessor):
    r"""
    Constructs a LLaVa image processor.

    Args:
        do_pad (`bool`, *optional*, defaults to `False`):
            Whether to pad the image to a square based on the longest edge.
            The padding value is determined by the `image_mean` parameter.
            Can be overridden by `do_pad` in the `preprocess` method.
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by
            `do_resize` in the `preprocess` method.
        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`):
            Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with
            the longest edge resized to keep the input aspect ratio. Can be overridden by `size` in the `preprocess`
            method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method.
        do_center_crop (`bool`, *optional*, defaults to `True`):
            Whether to center crop the image to the specified `crop_size`. Can be overridden by `do_center_crop` in the
            `preprocess` method.
        crop_size (`Dict[str, int]` *optional*, defaults to 224):
            Size of the output image after applying `center_crop`. Can be overridden by `crop_size` 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 `do_rescale` 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 `rescale_factor` in the `preprocess`
            method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method.
        image_mean (`float` or `List[float]`, *optional*, defaults to `[0.48145466, 0.4578275, 0.40821073]`):
            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 `[0.26862954, 0.26130258, 0.27577711]`):
            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.
            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_pad: bool = False,
        do_resize: bool = True,
        size: Dict[str, int] = None,
        resample: PILImageResampling = PILImageResampling.BICUBIC,
        do_center_crop: bool = True,
        crop_size: Dict[str, int] = None,
        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: bool = True,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"shortest_edge": 224}
        size = get_size_dict(size, default_to_square=False)
        crop_size = crop_size if crop_size is not None else {"height": 224, "width": 224}
        crop_size = get_size_dict(crop_size, default_to_square=True, param_name="crop_size")

        self.do_pad = do_pad
        self.do_resize = do_resize
        self.size = size
        self.resample = resample
        self.do_center_crop = do_center_crop
        self.crop_size = crop_size
        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 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_pad",
            "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 pad_to_square(
        self,
        image: np.ndarray,
        background_color: Union[int, Tuple[int, int, int]] = 0,
        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.
            background_color (`int` or `Tuple[int, int, int]`, *optional*, defaults to 0):
                The color to use for the padding. Can be an integer for single channel or a
                tuple of integers representing for multi-channel images. If passed as integer
                in mutli-channel mode, it will default to `0` in subsequent channels.
            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.
                If unset, will use the inferred format of the input image.

        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)

        # Ensure background_color is the correct shape
        if isinstance(background_color, int):
            background_color = [background_color]
        elif len(background_color) != num_channels:
            raise ValueError(
                f"background_color must have no more than {num_channels} elements to match the number of channels"
            )

        if input_data_format == ChannelDimension.FIRST:
            result = np.zeros((num_channels, max_dim, max_dim), dtype=image.dtype)
            for i, color in enumerate(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(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

        image = (
            to_channel_dimension_format(result, data_format, input_data_format) if data_format is not None else result
        )
        return image

    # Copied from transformers.models.clip.image_processing_clip.CLIPImageProcessor.resize
    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. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge
        resized to keep the input aspect ratio.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                Resampling filter to use when resiizing the image.
            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 (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        """
        default_to_square = True
        if "shortest_edge" in size:
            size = size["shortest_edge"]
            default_to_square = False
        elif "height" in size and "width" in size:
            size = (size["height"], size["width"])
        else:
            raise ValueError("Size must contain either 'shortest_edge' or 'height' and 'width'.")

        output_size = get_resize_output_image_size(
            image,
            size=size,
            default_to_square=default_to_square,
            input_data_format=input_data_format,
        )
        return resize(
            image,
            size=output_size,
            resample=resample,
            data_format=data_format,
            input_data_format=input_data_format,
            **kwargs,
        )

    def preprocess(
        self,
        images: ImageInput,
        do_pad: Optional[bool] = None,
        do_resize: Optional[bool] = None,
        size: Optional[Dict[str, int]] = None,
        resample: Optional[PILImageResampling] = None,
        do_center_crop: Optional[bool] = None,
        crop_size: Optional[int] = 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,
        do_convert_rgb: Optional[bool] = None,
        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.

        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_pad (`bool`, *optional*, defaults to `self.do_pad`):
                Whether to pad the image to a square based on the longest edge.
                The padding value is determined by the `image_mean` parameter.
            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. Shortest edge of the image is resized to size["shortest_edge"], with
                the longest edge resized to keep the input aspect ratio.
            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_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`):
                Whether to center crop the image.
            crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`):
                Size of the center crop. Only has an effect if `do_center_crop` 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 to use for normalization. Only has an effect if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to use for normalization. Only has an effect 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_pad = do_pad if do_pad is not None else self.do_pad
        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, param_name="size", default_to_square=False)
        resample = resample if resample is not None else self.resample
        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", default_to_square=True)
        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

        validate_kwargs(captured_kwargs=kwargs.keys(), valid_processor_keys=self._valid_processor_keys)

        images = make_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."
            )
        # we don't pass `do_pad` here since LLaVa uses a custom padding to a square
        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,
        )

        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 is_scaled_image(images[0]) and do_rescale:
            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])

        processed_images = []
        for image in images:
            if do_pad:
                image = self.pad_to_square(
                    image=image,
                    background_color=tuple(int(x * 255) for x in self.image_mean),
                    input_data_format=input_data_format,
                )

            if do_resize:
                image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format)

            if do_center_crop:
                image = self.center_crop(image=image, size=crop_size, 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)
            processed_images.append(image)

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


__all__ = ["LlavaImageProcessor"]