transformers_4_35_0/models/convnext/image_processing_convnext.py

# coding=utf-8
# Copyright 2022 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 ConvNeXT."""

from typing import Dict, List, Optional, Union

import numpy as np

from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from ...image_transforms import (
    center_crop,
    get_resize_output_image_size,
    resize,
    to_channel_dimension_format,
)
from ...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 ...utils import TensorType, is_vision_available, logging


if is_vision_available():
    import PIL


logger = logging.get_logger(__name__)


class ConvNextImageProcessor(BaseImageProcessor):
    r"""
    Constructs a ConvNeXT image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Controls whether to resize the image's (height, width) dimensions to the specified `size`. Can be overriden
            by `do_resize` in the `preprocess` method.
        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 384}`):
            Resolution of the output image after `resize` is applied. If `size["shortest_edge"]` >= 384, the image is
            resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will
            be matched to `int(size["shortest_edge"]/crop_pct)`, after which the image is cropped to
            `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. Can
            be overriden by `size` in the `preprocess` method.
        crop_pct (`float` *optional*, defaults to 224 / 256):
            Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size < 384. Can be
            overriden by `crop_pct` in the `preprocess` method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overriden 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 overriden 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 overriden by `rescale_factor` 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.
    """

    model_input_names = ["pixel_values"]

    def __init__(
        self,
        do_resize: bool = True,
        size: Dict[str, int] = None,
        crop_pct: float = 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 {"shortest_edge": 384}
        size = get_size_dict(size, default_to_square=False)

        self.do_resize = do_resize
        self.size = size
        # Default value set here for backwards compatibility where the value in config is None
        self.crop_pct = crop_pct if crop_pct is not None else 224 / 256
        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 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],
        crop_pct: float,
        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.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Dictionary of the form `{"shortest_edge": int}`, specifying the size of the output image. If
                `size["shortest_edge"]` >= 384 image is resized to `(size["shortest_edge"], size["shortest_edge"])`.
                Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"] / crop_pct)`,
                after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`.
            crop_pct (`float`):
                Percentage of the image to crop. Only has an effect if size < 384.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                Resampling filter to use when resizing 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 from the input
                image.
        """
        size = get_size_dict(size, default_to_square=False)
        if "shortest_edge" not in size:
            raise ValueError(f"Size dictionary must contain 'shortest_edge' key. Got {size.keys()}")
        shortest_edge = size["shortest_edge"]

        if shortest_edge < 384:
            # maintain same ratio, resizing shortest edge to shortest_edge/crop_pct
            resize_shortest_edge = int(shortest_edge / crop_pct)
            resize_size = get_resize_output_image_size(
                image, size=resize_shortest_edge, default_to_square=False, input_data_format=input_data_format
            )
            image = resize(
                image=image,
                size=resize_size,
                resample=resample,
                data_format=data_format,
                input_data_format=input_data_format,
                **kwargs,
            )
            # then crop to (shortest_edge, shortest_edge)
            return center_crop(
                image=image,
                size=(shortest_edge, shortest_edge),
                data_format=data_format,
                input_data_format=input_data_format,
                **kwargs,
            )
        else:
            # warping (no cropping) when evaluated at 384 or larger
            return resize(
                image,
                size=(shortest_edge, shortest_edge),
                resample=resample,
                data_format=data_format,
                input_data_format=input_data_format,
                **kwargs,
            )

    def preprocess(
        self,
        images: ImageInput,
        do_resize: bool = None,
        size: Dict[str, int] = None,
        crop_pct: float = 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,
        return_tensors: Optional[Union[str, TensorType]] = None,
        data_format: 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 output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image
                is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the
                image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to
                `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`.
            crop_pct (`float`, *optional*, defaults to `self.crop_pct`):
                Percentage of the image to crop if size < 384.
            resample (`int`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of `PILImageResampling`, filters. 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.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation.
            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
        crop_pct = crop_pct if crop_pct is not None else self.crop_pct
        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

        size = size if size is not None else self.size
        size = get_size_dict(size, default_to_square=False)

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

        if do_resize and size["shortest_edge"] < 384 and crop_pct is None:
            raise ValueError("crop_pct must be specified if size < 384.")

        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.")

        # 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, crop_pct=crop_pct, resample=resample, input_data_format=input_data_format
                )
                for image in images
            ]

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

        if do_normalize:
            images = [
                self.normalize(image=image, mean=image_mean, std=image_std, input_data_format=input_data_format)
                for image in images
            ]

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

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