Lightstar/venv/Lib/site-packages/transformers/models/vivit/image_processing_vivit.py

# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team.
#
# 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 Vivit."""

from typing import Dict, List, Optional, Union

import numpy as np

from transformers.utils import is_vision_available
from transformers.utils.generic import TensorType

from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from ...image_transforms import (
    get_resize_output_image_size,
    rescale,
    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,
    is_valid_image,
    to_numpy_array,
    valid_images,
    validate_preprocess_arguments,
)
from ...utils import filter_out_non_signature_kwargs, logging


if is_vision_available():
    import PIL

logger = logging.get_logger(__name__)


def make_batched(videos) -> List[List[ImageInput]]:
    if isinstance(videos, (list, tuple)) and isinstance(videos[0], (list, tuple)) and is_valid_image(videos[0][0]):
        return videos

    elif isinstance(videos, (list, tuple)) and is_valid_image(videos[0]):
        return [videos]

    elif is_valid_image(videos):
        return [[videos]]

    raise ValueError(f"Could not make batched video from {videos}")


class VivitImageProcessor(BaseImageProcessor):
    r"""
    Constructs a Vivit 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 the
            `do_resize` parameter in the `preprocess` method.
        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 256}`):
            Size of the output image after resizing. The shortest edge of the image will be resized to
            `size["shortest_edge"]` while maintaining the aspect ratio of the original image. Can be overriden by
            `size` 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_center_crop (`bool`, *optional*, defaults to `True`):
            Whether to center crop the image to the specified `crop_size`. Can be overridden by the `do_center_crop`
            parameter in the `preprocess` method.
        crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`):
            Size of the image after applying the center crop. Can be overridden by the `crop_size` 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 `1/127.5`):
            Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter
            in the `preprocess` method.
        offset (`bool`, *optional*, defaults to `True`):
            Whether to scale the image in both negative and positive directions. Can be overriden by the `offset` 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,
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        do_center_crop: bool = True,
        crop_size: Dict[str, int] = None,
        do_rescale: bool = True,
        rescale_factor: Union[int, float] = 1 / 127.5,
        offset: bool = True,
        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": 256}
        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.do_center_crop = do_center_crop
        self.crop_size = crop_size
        self.resample = resample
        self.do_rescale = do_rescale
        self.rescale_factor = rescale_factor
        self.offset = offset
        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],
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        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]`):
                Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will
                have the size `(h, w)`. If `size` is of the form `{"shortest_edge": s}`, the output image will have its
                shortest edge of length `s` while keeping the aspect ratio of the original image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
                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 (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        """
        size = get_size_dict(size, default_to_square=False)
        if "shortest_edge" in size:
            output_size = get_resize_output_image_size(
                image, size["shortest_edge"], default_to_square=False, input_data_format=input_data_format
            )
        elif "height" in size and "width" in size:
            output_size = (size["height"], size["width"])
        else:
            raise ValueError(f"Size must have 'height' and 'width' or 'shortest_edge' as keys. Got {size.keys()}")
        return resize(
            image,
            size=output_size,
            resample=resample,
            data_format=data_format,
            input_data_format=input_data_format,
            **kwargs,
        )

    # Copied from transformers.models.efficientnet.image_processing_efficientnet.EfficientNetImageProcessor.rescale
    def rescale(
        self,
        image: np.ndarray,
        scale: Union[int, float],
        offset: bool = True,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ):
        """
        Rescale an image by a scale factor.

        If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is
        1/127.5, the image is rescaled between [-1, 1].
            image = image * scale - 1

        If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1].
            image = image * scale

        Args:
            image (`np.ndarray`):
                Image to rescale.
            scale (`int` or `float`):
                Scale to apply to the image.
            offset (`bool`, *optional*):
                Whether to scale the image in both negative and positive directions.
            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.
        """
        rescaled_image = rescale(
            image, scale=scale, data_format=data_format, input_data_format=input_data_format, **kwargs
        )

        if offset:
            rescaled_image = rescaled_image - 1

        return rescaled_image

    def _preprocess_image(
        self,
        image: ImageInput,
        do_resize: bool = None,
        size: Dict[str, int] = None,
        resample: PILImageResampling = None,
        do_center_crop: bool = None,
        crop_size: Dict[str, int] = None,
        do_rescale: bool = None,
        rescale_factor: float = None,
        offset: bool = None,
        do_normalize: bool = None,
        image_mean: Optional[Union[float, List[float]]] = None,
        image_std: Optional[Union[float, List[float]]] = None,
        data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> np.ndarray:
        """Preprocesses a single image."""

        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,
        )

        if offset and not do_rescale:
            raise ValueError("For offset, do_rescale must also be set to True.")

        # All transformations expect numpy arrays.
        image = to_numpy_array(image)

        if is_scaled_image(image) 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:
            input_data_format = infer_channel_dimension_format(image)

        if do_resize:
            image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format)

        if do_center_crop:
            image = self.center_crop(image, size=crop_size, input_data_format=input_data_format)

        if do_rescale:
            image = self.rescale(image=image, scale=rescale_factor, offset=offset, input_data_format=input_data_format)

        if do_normalize:
            image = self.normalize(image=image, mean=image_mean, std=image_std, input_data_format=input_data_format)

        image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format)
        return image

    @filter_out_non_signature_kwargs()
    def preprocess(
        self,
        videos: ImageInput,
        do_resize: bool = None,
        size: Dict[str, int] = None,
        resample: PILImageResampling = None,
        do_center_crop: bool = None,
        crop_size: Dict[str, int] = None,
        do_rescale: bool = None,
        rescale_factor: float = None,
        offset: bool = 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,
    ) -> PIL.Image.Image:
        """
        Preprocess an image or batch of images.

        Args:
            videos (`ImageInput`):
                Video frames to preprocess. Expects a single or batch of video frames with pixel values ranging from 0
                to 255. If passing in frames 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 applying resize.
            resample (`PILImageResampling`, *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_center_crop (`bool`, *optional*, defaults to `self.do_centre_crop`):
                Whether to centre crop the image.
            crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`):
                Size of the image after applying the centre crop.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image values between `[-1 - 1]` if `offset` is `True`, `[0, 1]` otherwise.
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to rescale the image by if `do_rescale` is set to `True`.
            offset (`bool`, *optional*, defaults to `self.offset`):
                Whether to scale the image in both negative and positive directions.
            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:
                    - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                    - `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                    - Unset: Use the inferred 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
        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
        offset = offset if offset is not None else self.offset
        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")

        if not valid_images(videos):
            raise ValueError(
                "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                "torch.Tensor, tf.Tensor or jax.ndarray."
            )

        videos = make_batched(videos)

        videos = [
            [
                self._preprocess_image(
                    image=img,
                    do_resize=do_resize,
                    size=size,
                    resample=resample,
                    do_center_crop=do_center_crop,
                    crop_size=crop_size,
                    do_rescale=do_rescale,
                    rescale_factor=rescale_factor,
                    offset=offset,
                    do_normalize=do_normalize,
                    image_mean=image_mean,
                    image_std=image_std,
                    data_format=data_format,
                    input_data_format=input_data_format,
                )
                for img in video
            ]
            for video in videos
        ]

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