image_processing_vectorllm.py

from typing import Optional, Union

import numpy as np

from transformers.image_processing_utils import BaseImageProcessor, BatchFeature
from transformers.image_transforms import (
    convert_to_rgb,
    resize,
    to_channel_dimension_format,
)
from transformers.image_utils import (
    OPENAI_CLIP_MEAN,
    OPENAI_CLIP_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    get_image_size,
    infer_channel_dimension_format,
    is_scaled_image,
    make_flat_list_of_images,
    to_numpy_array,
    valid_images,
)
from transformers.utils import TensorType, logging


logger = logging.get_logger(__name__)


class VectorLLMImageProcessor(BaseImageProcessor):
    r"""
    Constructs a Qwen2-VL image processor that dynamically resizes images based on the original images.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions.
        size (`dict[str, int]`, *optional*, defaults to `{"shortest_edge": 56 * 56, "longest_edge": 28 * 28 * 1280}`):
            Size of the image after resizing. `shortest_edge` and `longest_edge` keys must be present.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use when resizing the image.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image by the specified scale `rescale_factor`.
        rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
            Scale factor to use if rescaling the image.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image.
        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 for each channel in the image.
        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 for each channel in the image.
        do_convert_rgb (`bool`, *optional*, defaults to `True`):
            Whether to convert the image to RGB.
        min_pixels (`int`, *optional*, defaults to `56 * 56`):
            The min pixels of the image to resize the image.
        max_pixels (`int`, *optional*, defaults to `28 * 28 * 1280`):
            The max pixels of the image to resize the image.
        patch_size (`int`, *optional*, defaults to 14):
            The spatial patch size of the vision encoder.
        temporal_patch_size (`int`, *optional*, defaults to 2):
            The temporal patch size of the vision encoder.
        merge_size (`int`, *optional*, defaults to 2):
            The merge size of the vision encoder to llm encoder.
    """

    model_input_names = ["pixel_values"]

    def __init__(
        self,
        do_resize: bool = True,
        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: bool = True,
        resized_size: int = 128,
        patch_size: int = 16,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        self.resized_size = resized_size

        self.do_resize = do_resize
        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 OPENAI_CLIP_MEAN
        self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD

        self.patch_size = patch_size
        self.do_convert_rgb = do_convert_rgb

    def _preprocess(
        self,
        images: Union[ImageInput],
        do_resize: Optional[bool] = 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,
        patch_size: Optional[int] = None,
        resized_size: Optional[int] = None,
        do_convert_rgb: Optional[bool] = None,
        data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ):
        """
        Preprocess an image or batch of images. Copy of the `preprocess` method from `CLIPImageProcessor`.

        Args:
            images (`ImageInput`):
                Image or batch of images to preprocess. Expects pixel values ranging from 0 to 255. If pixel values range from 0 to 1, set `do_rescale=False`.
            vision_info (`list[Dict]`, *optional*):
                Optional list of dictionaries containing additional information about vision inputs.
            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` and `longest_edge` keys must be present.
            resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the `PILImageResampling` enums.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image.
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Scale factor to use if rescaling the image.
            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`):
                Mean to use if normalizing the image. Can be a float or a list of floats corresponding to the number of channels in the image.
            image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
                Standard deviation to use if normalizing the image. Can be a float or a list of floats corresponding to the number of channels in the image.
            patch_size (`int`, *optional*, defaults to `self.patch_size`):
                The spatial patch size of the vision encoder.
            temporal_patch_size (`int`, *optional*, defaults to `self.temporal_patch_size`):
                The temporal patch size of the vision encoder.
            merge_size (`int`, *optional*, defaults to `self.merge_size`):
                The merge size of the vision encoder to llm encoder.
            do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
                Whether to convert the image to RGB.
            data_format (`ChannelDimension`, *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. 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.   - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
        """
        images = make_flat_list_of_images(images)

        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])

        height, width = get_image_size(images[0], channel_dim=input_data_format)
        resized_height, resized_width = height, width
        processed_images = []
        for image in images:
            if do_resize:
                resized_height, resized_width = resized_size, resized_size
                image = resize(
                    image, size=(resized_height, resized_width), resample=resample, input_data_format=input_data_format
                )

            if do_rescale:
                image = self.rescale(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 processed_images

    def preprocess(
        self,
        images: ImageInput,
        do_resize: Optional[bool] = 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,
        patch_size: Optional[int] = None,
        resized_size: Optional[int] = 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,
    ):
        """
        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`):
                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_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`.
            min_pixels (`int`, *optional*, defaults to `self.min_pixels`):
                The min pixels of the image to resize the image.
            max_pixels (`int`, *optional*, defaults to `self.max_pixels`):
                The max pixels of the image to resize the image.
            patch_size (`int`, *optional*, defaults to `self.patch_size`):
                The spatial patch size of the vision encoder.
            temporal_patch_size (`int`, *optional*, defaults to `self.temporal_patch_size`):
                The temporal patch size of the vision encoder.
            merge_size (`int`, *optional*, defaults to `self.merge_size`):
                The merge size of the vision encoder to llm encoder.
            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.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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
        resized_size = resized_size if resized_size is not None else self.resized_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
        patch_size = patch_size if patch_size is not None else self.patch_size
        do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb

        if images is not None:
            images = self.fetch_images(images)
            images = make_flat_list_of_images(images)

        if images is not None and not valid_images(images):
            raise ValueError("Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor")

        data = {}
        if images is not None:
            pixel_values = []
            for image in images:
                patches = self._preprocess(
                    image,
                    do_resize=do_resize,
                    resample=resample,
                    do_rescale=do_rescale,
                    rescale_factor=rescale_factor,
                    do_normalize=do_normalize,
                    image_mean=image_mean,
                    image_std=image_std,
                    patch_size=patch_size,
                    resized_size=resized_size,
                    data_format=data_format,
                    do_convert_rgb=do_convert_rgb,
                    input_data_format=input_data_format,
                )
                pixel_values.extend(patches)
            pixel_values = np.array(pixel_values)
            data.update({"pixel_values": pixel_values})

        return BatchFeature(data=data, tensor_type=return_tensors)

    def get_number_of_image_patches(self, height: int, width: int, images_kwargs=None):
        """
        A utility that returns number of image patches for a given image size.

        Args:
            height (`int`):
                Height of the input image.
            width (`int`):
                Width of the input image.
            images_kwargs (`dict`, *optional*)
                Any kwargs to override defaults of the image processor.
        Returns:
            `int`: Number of image patches per image.
        """
        resized_size = images_kwargs["resized_size"] if "resized_size" in images_kwargs else self.resized_size
        patch_size = images_kwargs["patch_size"] if "patch_size" in images_kwargs else self.patch_size

        return (resized_size // patch_size) ** 2

__all__ = ["VectorLLMImageProcessor"]