preprocessing_adaptformer.py

from typing import Tuple

from transformers import ViTImageProcessor
from transformers.image_processing_utils import BatchFeature
from transformers.image_utils import ImageInput


class AdaptFormerImageProcessor(ViTImageProcessor):
    r"""
    Constructs a AdaptFormer image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `(size["height"],
            size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method.
        size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`):
            Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
            method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            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`):
            Scale factor to use if rescaling the image. 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.
        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.
    """

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)

    def preprocess(
        self,
        images: Tuple[ImageInput, ImageInput],
        **kwargs,
    ) -> BatchFeature:
        """
        Preprocess an image or batch of images.

        Args:
            images (`Tuple[ImageInput, ImageInput]`):
                Image Tuple 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`):
                Dictionary in the format `{"height": h, "width": w}` specifying the size of the output image after
                resizing.
            resample (`PILImageResampling` filter, *optional*, defaults to `self.resample`):
                `PILImageResampling` filter to use if resizing the image e.g. `PILImageResampling.BILINEAR`. 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 use if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to use 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.
        """
        imagesA, imagesB = images
        feature_A = super().preprocess(imagesA, **kwargs)
        feature_B = super().preprocess(imagesB, **kwargs)

        data = {
            "pixel_valuesA": feature_A["pixel_values"],
            "pixel_valuesB": feature_B["pixel_values"],
        }
        return BatchFeature(data=data, tensor_type=kwargs.pop("return_tensors", None))