image_processing_spice_cnn.py

from typing import Dict, List, Optional, Union

import numpy as np

from transformers.image_processing_utils import (
    BaseImageProcessor,
    BatchFeature,
    get_size_dict,
)
from transformers.image_transforms import (
    normalize,
    rescale,
    resize,
    to_channel_dimension_format,
)
from transformers.image_utils import (
    IMAGENET_STANDARD_MEAN,
    IMAGENET_STANDARD_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    make_list_of_images,
    to_numpy_array,
    valid_images,
)
from transformers.utils import TensorType


class SpiceCNNImageProcessor(BaseImageProcessor):
    """
    Constructs a SpiceCNN 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 `PILImageResampling.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.
    """  # noqa

    def __init__(
        self,
        do_resize: bool = True,
        size: Optional[Dict[str, int]] = None,
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        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,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"height": 224, "width": 224}
        size = get_size_dict(size)
        self.do_resize = do_resize
        self.do_rescale = do_rescale
        self.do_normalize = do_normalize
        self.size = size
        self.resample = resample
        self.rescale_factor = rescale_factor
        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

    def resize(
        self,
        image: np.ndarray,
        size: Dict[str, int],
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ) -> np.ndarray:
        """
        Resize an image to `(size["height"], size["width"])`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
            resample:
                `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`.
            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.

        Returns:
            `np.ndarray`: The resized image.
        """  # noqa
        size = get_size_dict(size)
        if "height" not in size or "width" not in size:
            raise ValueError(
                f"The `size` dictionary must contain the keys `height` and `width`. Got {size.keys()}"  # noqa
            )
        return resize(
            image,
            size=(size["height"], size["width"]),
            resample=resample,
            data_format=data_format,
            **kwargs,
        )

    def rescale(
        self,
        image: np.ndarray,
        scale: float,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ) -> np.ndarray:
        """
        Rescale an image by a scale factor. image = image * scale.

        Args:
            image (`np.ndarray`):
                Image to rescale.
            scale (`float`):
                The scaling factor to rescale pixel values by.
            data_format (`str` or `ChannelDimension`, *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.

        Returns:
            `np.ndarray`: The rescaled image.
        """  # noqa
        return rescale(image, scale=scale, data_format=data_format, **kwargs)

    def normalize(
        self,
        image: np.ndarray,
        mean: Union[float, List[float]],
        std: Union[float, List[float]],
        data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ) -> np.ndarray:
        """
        Normalize an image. image = (image - image_mean) / image_std.

        Args:
            image (`np.ndarray`):
                Image to normalize.
            mean (`float` or `List[float]`):
                Image mean to use for normalization.
            std (`float` or `List[float]`):
                Image standard deviation to use for normalization.
            data_format (`str` or `ChannelDimension`, *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.

        Returns:
            `np.ndarray`: The normalized image.
        """  # noqa
        return normalize(image, mean=mean, std=std, data_format=data_format, **kwargs)

    def preprocess(
        self,
        images: ImageInput,
        do_resize: Optional[bool] = None,
        size: 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,
        data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
        **kwargs,
    ):
        """
        Preprocess an image or batch of images.

        Args:
            images (`ImageInput`):
                Image to preprocess.
            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.
        """  # noqa
        do_resize = do_resize if do_resize is not None else self.do_resize
        do_rescale = do_rescale if do_rescale is not None else self.do_rescale
        do_normalize = do_normalize if do_normalize is not None else self.do_normalize
        resample = resample if resample is not None else self.resample
        rescale_factor = (
            rescale_factor if rescale_factor is not None else self.rescale_factor
        )
        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

        size = size if size is not None else self.size
        size_dict = get_size_dict(size)

        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.")

        # All transformations expect numpy arrays.
        images = [to_numpy_array(image) for image in images]

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

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

        if do_normalize:
            images = [
                self.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)