# 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 MobileViT.""" from typing import Dict, List, Optional, Tuple, Union import numpy as np from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict from ...image_transforms import flip_channel_order, get_resize_output_image_size, resize, to_channel_dimension_format from ...image_utils import ( 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, is_torch_available, is_torch_tensor, is_vision_available, logging, ) if is_vision_available(): import PIL if is_torch_available(): import torch logger = logging.get_logger(__name__) class MobileViTImageProcessor(BaseImageProcessor): r""" Constructs a MobileViT 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": 224}`): Controls the size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Defines the 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_center_crop (`bool`, *optional*, defaults to `True`): Whether to crop the input at the center. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 256, "width": 256}`): Desired output size `(size["height"], size["width"])` when applying center-cropping. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_flip_channel_order (`bool`, *optional*, defaults to `True`): Whether to flip the color channels from RGB to BGR. Can be overridden by the `do_flip_channel_order` 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_rescale: bool = True, rescale_factor: Union[int, float] = 1 / 255, do_center_crop: bool = True, crop_size: Dict[str, int] = None, do_flip_channel_order: bool = True, **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": 256, "width": 256} crop_size = get_size_dict(crop_size, param_name="crop_size") self.do_resize = do_resize self.size = size self.resample = resample self.do_rescale = do_rescale self.rescale_factor = rescale_factor self.do_center_crop = do_center_crop self.crop_size = crop_size self.do_flip_channel_order = do_flip_channel_order # Copied from transformers.models.mobilenet_v1.image_processing_mobilenet_v1.MobileNetV1ImageProcessor.resize with PILImageResampling.BICUBIC->PILImageResampling.BILINEAR 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. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output 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 (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. """ default_to_square = True if "shortest_edge" in size: size = size["shortest_edge"] default_to_square = False elif "height" in size and "width" in size: size = (size["height"], size["width"]) else: raise ValueError("Size must contain either 'shortest_edge' or 'height' and 'width'.") output_size = get_resize_output_image_size( image, size=size, default_to_square=default_to_square, input_data_format=input_data_format, ) return resize( image, size=output_size, resample=resample, data_format=data_format, input_data_format=input_data_format, **kwargs, ) def flip_channel_order( self, image: np.ndarray, data_format: Optional[Union[str, ChannelDimension]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> np.ndarray: """ Flip the color channels from RGB to BGR or vice versa. Args: image (`np.ndarray`): The image, represented as a numpy array. data_format (`ChannelDimension` or `str`, *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. """ return flip_channel_order(image, data_format=data_format, input_data_format=input_data_format) def __call__(self, images, segmentation_maps=None, **kwargs): """ Preprocesses a batch of images and optionally segmentation maps. Overrides the `__call__` method of the `Preprocessor` class so that both images and segmentation maps can be passed in as positional arguments. """ return super().__call__(images, segmentation_maps=segmentation_maps, **kwargs) def _preprocess( self, image: ImageInput, do_resize: bool, do_rescale: bool, do_center_crop: bool, do_flip_channel_order: bool, size: Optional[Dict[str, int]] = None, resample: PILImageResampling = None, rescale_factor: Optional[float] = None, crop_size: Optional[Dict[str, int]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, ): 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_center_crop: image = self.center_crop(image=image, size=crop_size, input_data_format=input_data_format) if do_flip_channel_order: image = self.flip_channel_order(image, input_data_format=input_data_format) return image def _preprocess_image( self, image: 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_center_crop: Optional[bool] = None, crop_size: Dict[str, int] = None, do_flip_channel_order: Optional[bool] = None, data_format: Optional[Union[str, ChannelDimension]] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> np.ndarray: """Preprocesses a single 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 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) image = self._preprocess( image=image, do_resize=do_resize, size=size, resample=resample, do_rescale=do_rescale, rescale_factor=rescale_factor, do_center_crop=do_center_crop, crop_size=crop_size, do_flip_channel_order=do_flip_channel_order, input_data_format=input_data_format, ) image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format) return image def _preprocess_mask( self, segmentation_map: ImageInput, do_resize: Optional[bool] = None, size: Dict[str, int] = None, do_center_crop: Optional[bool] = None, crop_size: Dict[str, int] = None, input_data_format: Optional[Union[str, ChannelDimension]] = None, ) -> np.ndarray: """Preprocesses a single mask.""" segmentation_map = to_numpy_array(segmentation_map) # Add channel dimension if missing - needed for certain transformations if segmentation_map.ndim == 2: added_channel_dim = True segmentation_map = segmentation_map[None, ...] input_data_format = ChannelDimension.FIRST else: added_channel_dim = False if input_data_format is None: input_data_format = infer_channel_dimension_format(segmentation_map, num_channels=1) segmentation_map = self._preprocess( image=segmentation_map, do_resize=do_resize, size=size, resample=PILImageResampling.NEAREST, do_rescale=False, do_center_crop=do_center_crop, crop_size=crop_size, do_flip_channel_order=False, input_data_format=input_data_format, ) # Remove extra channel dimension if added for processing if added_channel_dim: segmentation_map = segmentation_map.squeeze(0) segmentation_map = segmentation_map.astype(np.int64) return segmentation_map @filter_out_non_signature_kwargs() def preprocess( self, images: ImageInput, segmentation_maps: Optional[ImageInput] = None, do_resize: Optional[bool] = None, size: Dict[str, int] = None, resample: PILImageResampling = None, do_rescale: Optional[bool] = None, rescale_factor: Optional[float] = None, do_center_crop: Optional[bool] = None, crop_size: Dict[str, int] = None, do_flip_channel_order: Optional[bool] = 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: 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`. segmentation_maps (`ImageInput`, *optional*): Segmentation map 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`): Size of the image after resizing. resample (`int`, *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_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image by rescale factor. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. 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 center crop if `do_center_crop` is set to `True`. do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`): Whether to flip the channel order of the image. 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. 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_center_crop = do_center_crop if do_center_crop is not None else self.do_center_crop do_flip_channel_order = ( do_flip_channel_order if do_flip_channel_order is not None else self.do_flip_channel_order ) 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 segmentation_maps is not None: segmentation_maps = make_list_of_images(segmentation_maps, expected_ndims=2) 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 segmentation_maps is not None and not valid_images(segmentation_maps): raise ValueError( "Invalid segmentation map 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_center_crop=do_center_crop, crop_size=crop_size, do_resize=do_resize, size=size, resample=resample, ) images = [ self._preprocess_image( image=img, do_resize=do_resize, size=size, resample=resample, do_rescale=do_rescale, rescale_factor=rescale_factor, do_center_crop=do_center_crop, crop_size=crop_size, do_flip_channel_order=do_flip_channel_order, data_format=data_format, input_data_format=input_data_format, ) for img in images ] data = {"pixel_values": images} if segmentation_maps is not None: segmentation_maps = [ self._preprocess_mask( segmentation_map=segmentation_map, do_resize=do_resize, size=size, do_center_crop=do_center_crop, crop_size=crop_size, input_data_format=input_data_format, ) for segmentation_map in segmentation_maps ] data["labels"] = segmentation_maps return BatchFeature(data=data, tensor_type=return_tensors) # Copied from transformers.models.beit.image_processing_beit.BeitImageProcessor.post_process_semantic_segmentation with Beit->MobileViT def post_process_semantic_segmentation(self, outputs, target_sizes: List[Tuple] = None): """ Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch. Args: outputs ([`MobileViTForSemanticSegmentation`]): Raw outputs of the model. target_sizes (`List[Tuple]` of length `batch_size`, *optional*): List of tuples corresponding to the requested final size (height, width) of each prediction. If unset, predictions will not be resized. Returns: semantic_segmentation: `List[torch.Tensor]` of length `batch_size`, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if `target_sizes` is specified). Each entry of each `torch.Tensor` correspond to a semantic class id. """ # TODO: add support for other frameworks logits = outputs.logits # Resize logits and compute semantic segmentation maps if target_sizes is not None: if len(logits) != len(target_sizes): raise ValueError( "Make sure that you pass in as many target sizes as the batch dimension of the logits" ) if is_torch_tensor(target_sizes): target_sizes = target_sizes.numpy() semantic_segmentation = [] for idx in range(len(logits)): resized_logits = torch.nn.functional.interpolate( logits[idx].unsqueeze(dim=0), size=target_sizes[idx], mode="bilinear", align_corners=False ) semantic_map = resized_logits[0].argmax(dim=0) semantic_segmentation.append(semantic_map) else: semantic_segmentation = logits.argmax(dim=1) semantic_segmentation = [semantic_segmentation[i] for i in range(semantic_segmentation.shape[0])] return semantic_segmentation __all__ = ["MobileViTImageProcessor"]