o Zh$@sdZddlmZmZddlZddlmZmZddl m Z m Z m Z ddl mZmZmZmZmZmZmZmZddlmZmZmZeeZGd d d eZd gZdS) z"Image processor class for Swin2SR.)OptionalUnionN)BaseImageProcessor BatchFeature)get_image_sizepadto_channel_dimension_format)ChannelDimension ImageInputinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingcseZdZdZdgZ    ddedeeefded ed d f fd d Z dde j dede ee efde ee effddZed d d d d ejd fdede ede ede ed e ede ee efdee efde ee effddZZS)Swin2SRImageProcessora Constructs a Swin2SR image processor. Args: 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. pixel_valuesTp? do_rescalerescale_factordo_padpad_sizereturnNc s.tjdi|||_||_||_||_dS)N)super__init__rrrr)selfrrrrkwargs __class__rc/var/www/auris/lib/python3.10/site-packages/transformers/models/swin2sr/image_processing_swin2sr.pyr 6s  zSwin2SRImageProcessor.__init__imagesize data_formatinput_data_formatc CsTt||\}}||d||}||d||}t|d|fd|ffd||dS)a Pad an image to make the height and width divisible by `size`. Args: image (`np.ndarray`): Image to pad. size (`int`): The size to make the height and width divisible by. data_format (`str` or `ChannelDimension`, *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. input_data_format (`str` or `ChannelDimension`, *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. Returns: `np.ndarray`: The padded image. rZ symmetric)moder(r))rr) r!r&r'r(r)Z old_heightZ old_widthZ pad_heightZ pad_widthrrr%rEszSwin2SRImageProcessor.padimagesreturn_tensorsc s|dur|nj}durnj|dur|nj}dur!njt|}t|s0tdt||ddd|D}|rLt|drLt ddurVt |d|rcfdd|D}|rpfd d|D}fd d|D}d |i} t | |d S) a 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_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_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to make the height and width divisible by `window_size`. pad_size (`int`, *optional*, defaults to 32): The size of the sliding window for the local attention. 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 typ, input_data_format=input_data_formate `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. NzkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rrrZsize_divisibilitycSsg|]}t|qSr)r.0r&rrr% sz4Swin2SRImageProcessor.preprocess..rzIt 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.cg|] }j|dqS))r&scaler))Zrescaler.)r)rr!rr%r0scr1))r'r))rr.)r)rr!rr%r0scsg|] }t|dqS))Zinput_channel_dim)r r.)r(r)rr%r0sr)dataZ tensor_type) rrrrrr ValueErrorrr loggerZ warning_oncer r) r!r,rrrrr-r(r)r3r)r(r)rrr!r% preprocessnsB/   z Swin2SRImageProcessor.preprocess)TrTr)NN)__name__ __module__ __qualname____doc__Zmodel_input_namesboolrintfloatr npZndarrayrstrr rrZFIRSTr rr6 __classcell__rrr#r%r'sl   )  r)r:typingrrnumpyr>Zimage_processing_utilsrrZimage_transformsrrr Z image_utilsr r r r rrrrutilsrrrZ get_loggerr7r5r__all__rrrr%s(  (