# coding=utf-8 # Copyright 2024 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 InstructBLIPVideo. Largely copy of Blip2Processor with addition of a video processing abilities """ 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 convert_to_rgb, resize, to_channel_dimension_format from ...image_utils import ( OPENAI_CLIP_MEAN, OPENAI_CLIP_STD, ChannelDimension, ImageInput, PILImageResampling, VideoInput, infer_channel_dimension_format, is_scaled_image, make_batched_videos, to_numpy_array, valid_images, validate_preprocess_arguments, ) from ...utils import TensorType, filter_out_non_signature_kwargs, logging logger = logging.get_logger(__name__) # Copied from transformers.models.blip.image_processing_blip.BlipImageProcessor with Blip->InstructBlipVideo, BLIP->InstructBLIPVideo class InstructBlipVideoImageProcessor(BaseImageProcessor): r""" Constructs a InstructBLIPVideo 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`, *optional*, defaults to `{"height": 384, "width": 384}`): Size of the output image after resizing. 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. Only has an effect if `do_resize` is set to `True`. 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. Only has an effect if `do_rescale` is set to `True`. 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. 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. 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. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. """ model_input_names = ["pixel_values"] def __init__( self, do_resize: bool = True, size: Dict[str, int] = None, resample: PILImageResampling = PILImageResampling.BICUBIC, 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, do_convert_rgb: bool = True, **kwargs, ) -> None: super().__init__(**kwargs) size = size if size is not None else {"height": 384, "width": 384} size = get_size_dict(size, default_to_square=True) self.do_resize = do_resize self.size = size 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 OPENAI_CLIP_MEAN self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD self.do_convert_rgb = do_convert_rgb # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize with PILImageResampling.BILINEAR->PILImageResampling.BICUBIC 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 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`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. 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. - `"none"` or `ChannelDimension.NONE`: image in (height, width) 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. Returns: `np.ndarray`: The resized image. """ 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()}") output_size = (size["height"], size["width"]) return resize( image, size=output_size, resample=resample, data_format=data_format, input_data_format=input_data_format, **kwargs, ) # Ignore copy @filter_out_non_signature_kwargs() def preprocess( self, images: VideoInput = None, do_resize: Optional[bool] = None, size: Optional[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, do_convert_rgb: Optional[bool] = None, data_format: ChannelDimension = ChannelDimension.FIRST, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> BatchFeature: """ Preprocess a video or batch of images/videos. Args: videos (`VideoInput`): Video frames to preprocess. Expects a single or batch of videos as a list of frames with pixel values ranging from 0 to 255. If passing in video with pixel values between 0 and 1, set `do_rescale=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the video. size (`Dict[str, int]`, *optional*, defaults to `self.size`): Controls the size of the video after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the video. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the video values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the video by if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the video. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Image mean to normalize the video by if `do_normalize` is set to `True`. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to normalize the video by if `do_normalize` is set to `True`. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. 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 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 do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb size = size if size is not None else self.size size = get_size_dict(size, default_to_square=False) videos = make_batched_videos(images) validate_preprocess_arguments( do_rescale=do_rescale, rescale_factor=rescale_factor, do_normalize=do_normalize, image_mean=image_mean, image_std=image_std, do_resize=do_resize, size=size, resample=resample, ) if not valid_images(videos): raise ValueError( "Invalid input type. Must be of type PIL.Image.Image, numpy.ndarray, " "torch.Tensor, tf.Tensor or jax.ndarray." ) pixel_values = [ [ self._preprocess_image( image=frame, do_resize=do_resize, size=size, resample=resample, do_rescale=do_rescale, rescale_factor=rescale_factor, do_normalize=do_normalize, image_mean=image_mean, image_std=image_std, do_convert_rgb=do_convert_rgb, data_format=data_format, input_data_format=input_data_format, ) for frame in video ] for video in videos ] encoded_outputs = BatchFeature(data={"pixel_values": pixel_values}, tensor_type=return_tensors) return encoded_outputs # Ignore copy def _preprocess_image( self, image: ImageInput = None, do_resize: Optional[bool] = None, size: Optional[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, do_convert_rgb: Optional[bool] = None, data_format: ChannelDimension = ChannelDimension.FIRST, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> np.ndarray: # PIL RGBA images are converted to RGB if do_convert_rgb: image = convert_to_rgb(image) # All transformations expect numpy arrays. image = to_numpy_array(image) if do_rescale and is_scaled_image(image): logger.warning_once( "It looks like you are trying to rescale already rescaled video frames. 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(image) if do_resize: image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) if do_rescale: image = self.rescale(image=image, scale=rescale_factor, 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