`in&dZddlmZmZddlZddlmZmZddl m Z m Z m Z ddl mZmZmZmZmZmZmZmZddlmZmZmZdd lmZejeZGd 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_kwargceZdZdZdgZ ddedeeefded ed d f fd Z e d Z e j dZ dde jdedeeeefdeeeeffdZeeddd d d d d d ejd fdedeedeedeed eedeeeefdeeefdeeeeffdZxZS)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 tjdi|||_||_||_|d}||n||_dS)Npad_size)super__init__rrrgetr)selfrrrrkwargsr" __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/swin2sr/image_processing_swin2sr.pyr%zSwin2SRImageProcessor.__init__7s` ""6"""$, ::j)),8,DLL(cDtd|jSNzb`self.pad_size` attribute is deprecated and will be removed in v5. Use `self.size_divisor` insteadloggerwarningr)r's r*r"zSwin2SRImageProcessor.pad_sizeGs& p     r+cHtd||_dSr-r.)r'values r*r"zSwin2SRImageProcessor.pad_sizeNs+ p   "r+imagesize data_formatinput_data_formatct||\}}||zdz|z|z }||zdz|z|z }t|d|fd|ffd||S)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)moder5r6)rr ) r'r3r4r5r6 old_height old_width pad_height pad_widths r*r zSwin2SRImageProcessor.padUs~:!/u6G H H I D(1,4zA $&*d2Y>  _q)n -#/     r+r"v5)versionnew_nameimagesreturn_tensorsc ||nj}nj||nj}njt |}t |st dt|d|D}|r/t|drt dt|d|rfd|D}|rfd|D}fd |D}d |i} t| | 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.)rrc,g|]}t|Sr#)r).0r3s r* z4Swin2SRImageProcessor.preprocess..s <<.s< 5Rc ddr+c@g|]}|S))r4r6)r )rFr3r6r'rs r*rGz4Swin2SRImageProcessor.preprocess..s-rrrbgdhhu.s7   ej '{N_ ` ` `   r+r)data tensor_type) rrrrrr ValueErrorrrr/ warning_oncer r) r'rBrrrrrCr5r6rNs ` ` ` `` r* preprocessz Swin2SRImageProcessor.preprocess~s`$.#9ZZt +9+E4K^!-4;'3'?||TEV )&11F## :  &!)    =vay I I   #F  srrrrrrkqrrrF     nt   '>BBBBr+)TrTr)NN)__name__ __module__ __qualname____doc__model_input_namesboolrintfloatr%propertyr"setternpndarrayrstrr r rrFIRSTr rrR __classcell__)r)s@r*rr(s\  (( ,3 SSSc5j)S S  S SSSSSS !!X! _""_"?CDH ' ' z' ' eC)9$9:; ' $E#/?*?$@A ' ' ' ' R%$&&_ZGGG&**.!%&*;?4D4JDHZCZCZCTNZC! ZC  ZC sm ZC!sJ!78ZC3 001ZC$E#/?*?$@AZCZCZCHG'&ZCZCZCZCZCr+r)!rVtypingrrnumpyr]image_processing_utilsrrimage_transformsrr r image_utilsr r r rrrrrutilsrrrutils.deprecationr get_loggerrSr/r__all__r#r+r*rks\)(""""""""FFFFFFFFPPPPPPPPPP                    JIIIIIIIII000000  H % %rCrCrCrCrC.rCrCrCj # #r+