dam/model/multimodal_encoder/siglip/image_processing_siglip.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 SigLIP."""

from typing import Dict, List, Optional, Union

from transformers.image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from transformers.image_transforms import (
    center_crop,
    resize,
    rescale,
    normalize,
    to_channel_dimension_format,
    get_resize_output_image_size,
    get_channel_dimension_axis,
    convert_to_rgb,
)
from transformers.image_utils import (
    IMAGENET_STANDARD_MEAN,
    IMAGENET_STANDARD_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    infer_channel_dimension_format,
    # is_scaled_image,
    make_list_of_images,
    to_numpy_array,
    valid_images,
)
from transformers.utils import TensorType, is_vision_available, logging
import numpy as np

logger = logging.get_logger(__name__)

def is_scaled_image(image: np.ndarray) -> bool:
    """
    Checks to see whether the pixel values have already been rescaled to [0, 1].
    """
    if image.dtype == np.uint8:
        return False

    # It's possible the image has pixel values in [0, 255] but is of floating type
    return np.min(image) >= 0 and np.max(image) <= 1


if is_vision_available():
    import PIL


class SiglipImageProcessor(BaseImageProcessor):
    r"""
    Constructs a SigLIP 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
            `do_resize` 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 `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_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 by the specified mean and standard deviation. Can be overridden by
            `do_normalize` in the `preprocess` method.
        image_mean (`float` or `List[float]`, *optional*, defaults to `[0.5, 0.5, 0.5]`):
            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 `[0.5, 0.5, 0.5]`):
            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.
    """

    model_input_names = ["pixel_values"]

    def __init__(
        self,
        do_resize: bool = True,
        size: 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: bool = True,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"shortest_edge": 384}
        size = get_size_dict(size, default_to_square=False)
        image_mean = image_mean if image_mean is not None else IMAGENET_STANDARD_MEAN
        image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
        
        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
        self.image_std = image_std
        self.do_convert_rgb = do_convert_rgb

    def resize(
        self,
        image: np.ndarray,
        size: Dict[str, int],
        resample: PILImageResampling = PILImageResampling.BICUBIC,
        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.
        """
        # size = get_size_dict(size, default_to_square=False)
        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)
        return resize(image, size=output_size, resample=resample, data_format=data_format, **kwargs)

    def preprocess(
        self,
        images: ImageInput,
        do_resize: bool = None,
        size: Dict[str, int] = None,
        resample: PILImageResampling = None,
        do_rescale: bool = None,
        rescale_factor: float = None,
        do_normalize: bool = None,
        image_mean: Optional[Union[float, List[float]]] = None,
        image_std: Optional[Union[float, List[float]]] = None,
        do_convert_rgb: 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_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 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`.
            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
        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


        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."
            )

        if do_resize and size is None:
            raise ValueError("Size must be specified if do_resize is True.")

        if do_rescale and rescale_factor is None:
            raise ValueError("Rescale factor must be specified if do_rescale is True.")

        if do_normalize and (image_mean is None or image_std is None):
            raise ValueError("Image mean and std must be specified if do_normalize is True.")

        # 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 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])
        
        if do_resize:
            images = [self.resize(image=image, size=size, resample=resample) for image in images]

        if do_rescale:
            images = [rescale(image=image, scale=rescale_factor) for image in images]

        if do_normalize:
            output_images = []
            for image in images:
                if get_channel_dimension_axis(image) == 0:
                    image = image.transpose((1, 2, 0))
                if image.shape[-1] == 1:    
                    image = np.dstack((image, image, image))
                output_images.append(image)
            images = output_images
            # for image in images:
            # #     print("image shape", image.shape)
            #     channel_axis = get_channel_dimension_axis(image)
            #     num_channels = image.shape[channel_axis]
            #     if num_channels != len(image_mean):
            #         print("image_mean", image_mean)
            #         print("channel_axis", channel_axis)
            #         print("num_channels", num_channels)
            #         print("image.shape", image.shape)
            #         raise ValueError(
            #             f"Number of channels in the image ({num_channels}) does not match the length of image mean "
            #             f"({len(image_mean)})."
            #         )

            images = [normalize(image=image, mean=image_mean, std=image_std) for image in images]

        images = [to_channel_dimension_format(image, data_format) for image in images]


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