o in&@sdZddlmZmZddlZddlmZmZddl m Z m Z m Z ddl mZmZmZmZmZmZmZmZddlmZmZmZdd lmZeeZGd d d eZd gZ dS) z"Image processor class for Swin2SR.)OptionalUnionN)BaseImageProcessor BatchFeature)get_image_sizepadto_channel_dimension_format)ChannelDimension ImageInputinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)deprecate_kwargcs"eZdZdZdgZ    ddedeeefded ed d f fd d Z e ddZ e j ddZ dde jdedeeeefdeeeeffddZeeddd dd d d d d ejd fdedeedeedeed eedeeeefdeeefdeeeeffddZZS) 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_pad size_divisorreturnNc sJtjdi|||_||_||_|d}|dur ||_dS||_dS)Npad_size)super__init__rrrgetr)selfrrrrkwargsr __class__r h/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/swin2sr/image_processing_swin2sr.pyr"7s  zSwin2SRImageProcessor.__init__cCstd|jSNzb`self.pad_size` attribute is deprecated and will be removed in v5. Use `self.size_divisor` insteadloggerwarningr)r$r r r(rGszSwin2SRImageProcessor.pad_sizecCstd||_dSr)r*)r$valuer r r(rNs 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. r symmetric)moder0r1)rr) r$r.r/r0r1 old_height old_width pad_height pad_widthr r r(rUszSwin2SRImageProcessor.padrv5)versionnew_nameimagesreturn_tensorsc s|dur|nj}durnj|dur|nj}dur!njt|}t|s0tdt|ddd|D}|rJt|drJt ddurTt |d|rafdd|D}|rnfd 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`. size_divisor (`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_format `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.)rrcSsg|]}t|qSr )r.0r.r r r( 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.csg|] }j|dqS))r.scaler1)rescaler>)r1rr$r r(r@scsg|] }j|dqS))r/r1)rr>)r1r$rr r(r@scsg|] }t|dqS))input_channel_dim)r r>)r0r1r r(r@sr)data tensor_type) rrrrrr ValueErrorrr r+ warning_oncer r) r$r<rrrrr=r0r1rDr )r0r1rr$rr( preprocess~s>0   z Swin2SRImageProcessor.preprocess)TrTr)NN)__name__ __module__ __qualname____doc__model_input_namesboolrintfloatr"propertyrsetternpndarrayrstrr rrrFIRSTr rrH __classcell__r r r&r(r(sv      )   r)!rLtypingrrnumpyrSimage_processing_utilsrrimage_transformsrrr image_utilsr r r r rrrrutilsrrrutils.deprecationr get_loggerrIr+r__all__r r r r(s(   6