Lightstar/venv/Lib/site-packages/transformers/models/levit/image_processing_levit.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 LeViT."""

from typing import Dict, Iterable, Optional, Union

import numpy as np

from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from ...image_transforms import (
    get_resize_output_image_size,
    resize,
    to_channel_dimension_format,
)
from ...image_utils import (
    IMAGENET_DEFAULT_MEAN,
    IMAGENET_DEFAULT_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    infer_channel_dimension_format,
    is_scaled_image,
    make_list_of_images,
    to_numpy_array,
    valid_images,
    validate_preprocess_arguments,
)
from ...utils import TensorType, filter_out_non_signature_kwargs, logging


logger = logging.get_logger(__name__)


class LevitImageProcessor(BaseImageProcessor):
    r"""
    Constructs a LeViT image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Wwhether to resize the shortest edge of the input to int(256/224 *`size`). Can be overridden by the
            `do_resize` parameter in the `preprocess` method.
        size (`Dict[str, int]`, *optional*, defaults to `{"shortest_edge": 224}`):
            Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will
            be resized to `(size["height"], size["width"])`. If size is a dict with key "shortest_edge", the shortest
            edge value `c` is rescaled to `int(c * (256/224))`. The smaller edge of the image will be matched to this
            value i.e, if height > width, then image will be rescaled to `(size["shortest_egde"] * height / width,
            size["shortest_egde"])`. Can be overridden by the `size` parameter in the `preprocess` method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
            `preprocess` method.
        do_center_crop (`bool`, *optional*, defaults to `True`):
            Whether or not to center crop the input to `(crop_size["height"], crop_size["width"])`. Can be overridden
            by the `do_center_crop` parameter in the `preprocess` method.
        crop_size (`Dict`, *optional*, defaults to `{"height": 224, "width": 224}`):
            Desired image size after `center_crop`. Can be overridden by the `crop_size` parameter in the `preprocess`
            method.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Controls 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`):
            Controls whether to normalize the image. Can be overridden by the `do_normalize` parameter in the
            `preprocess` method.
        image_mean (`List[int]`, *optional*, defaults to `[0.485, 0.456, 0.406]`):
            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 (`List[int]`, *optional*, defaults to `[0.229, 0.224, 0.225]`):
            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,
        resample: PILImageResampling = PILImageResampling.BICUBIC,
        do_center_crop: bool = True,
        crop_size: Dict[str, int] = None,
        do_rescale: bool = True,
        rescale_factor: Union[int, float] = 1 / 255,
        do_normalize: bool = True,
        image_mean: Optional[Union[float, Iterable[float]]] = IMAGENET_DEFAULT_MEAN,
        image_std: Optional[Union[float, Iterable[float]]] = IMAGENET_DEFAULT_STD,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"shortest_edge": 224}
        size = get_size_dict(size, default_to_square=False)
        crop_size = crop_size if crop_size is not None else {"height": 224, "width": 224}
        crop_size = get_size_dict(crop_size, param_name="crop_size")

        self.do_resize = do_resize
        self.size = size
        self.resample = resample
        self.do_center_crop = do_center_crop
        self.crop_size = crop_size
        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_DEFAULT_MEAN
        self.image_std = image_std if image_std is not None else IMAGENET_DEFAULT_STD

    def resize(
        self,
        image: np.ndarray,
        size: Dict[str, int],
        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.

        If size is a dict with keys "width" and "height", the image will be resized to `(size["height"],
        size["width"])`.

        If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to `int(c * (256/224))`.
        The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled
        to `(size["shortest_egde"] * height / width, size["shortest_egde"])`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Size of the output image after resizing. If size is a dict with keys "width" and "height", the image
                will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value
                `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value
                i.e, if height > width, then image will be rescaled to (size * height / width, size).
            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.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        """
        size_dict = get_size_dict(size, default_to_square=False)
        # size_dict is a dict with either keys "height" and "width" or "shortest_edge"
        if "shortest_edge" in size:
            shortest_edge = int((256 / 224) * size["shortest_edge"])
            output_size = get_resize_output_image_size(
                image, size=shortest_edge, default_to_square=False, input_data_format=input_data_format
            )
            size_dict = {"height": output_size[0], "width": output_size[1]}
        if "height" not in size_dict or "width" not in size_dict:
            raise ValueError(
                f"Size dict must have keys 'height' and 'width' or 'shortest_edge'. Got {size_dict.keys()}"
            )
        return resize(
            image,
            size=(size_dict["height"], size_dict["width"]),
            resample=resample,
            data_format=data_format,
            input_data_format=input_data_format,
            **kwargs,
        )

    @filter_out_non_signature_kwargs()
    def preprocess(
        self,
        images: ImageInput,
        do_resize: Optional[bool] = None,
        size: Optional[Dict[str, int]] = None,
        resample: PILImageResampling = None,
        do_center_crop: Optional[bool] = None,
        crop_size: Optional[Dict[str, int]] = None,
        do_rescale: Optional[bool] = None,
        rescale_factor: Optional[float] = None,
        do_normalize: Optional[bool] = None,
        image_mean: Optional[Union[float, Iterable[float]]] = None,
        image_std: Optional[Union[float, Iterable[float]]] = None,
        return_tensors: Optional[TensorType] = None,
        data_format: ChannelDimension = ChannelDimension.FIRST,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> BatchFeature:
        """
        Preprocess an image or batch of images to be used as input to a LeViT model.

        Args:
            images (`ImageInput`):
                Image or batch of images 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 resizing. If size is a dict with keys "width" and "height", the image
                will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value
                `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value
                i.e, if height > width, then image will be rescaled to (size * height / width, size).
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                Resampling filter to use when resiizing the image.
            do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`):
                Whether to center crop the image.
            crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`):
                Size of the output image after center cropping. Crops images to (crop_size["height"],
                crop_size["width"]).
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image pixel values by `rescaling_factor` - typical to values between 0 and 1.
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Factor to rescale the image pixel values by.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image pixel values by `image_mean` and `image_std`.
            image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`):
                Mean to normalize the image pixel values by.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Standard deviation to normalize the image pixel values by.
            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 (`str` or `ChannelDimension`, *optional*, defaults to `ChannelDimension.FIRST`):
                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.
            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
        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
        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)
        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")
        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."
            )
        validate_preprocess_arguments(
            do_rescale=do_rescale,
            rescale_factor=rescale_factor,
            do_normalize=do_normalize,
            image_mean=image_mean,
            image_std=image_std,
            do_center_crop=do_center_crop,
            crop_size=crop_size,
            do_resize=do_resize,
            size=size,
            resample=resample,
        )
        # 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, size, resample, input_data_format=input_data_format) for image in images]

        if do_center_crop:
            images = [self.center_crop(image, crop_size, input_data_format=input_data_format) for image in images]

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

        if do_normalize:
            images = [
                self.normalize(image, image_mean, 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)