qi>#dZddlZddlmZmZddlmZmZm Z ddl m Z m Z m Z mZmZmZmZmZddlmZddlmZmZmZej2eZGd d ed ZGd deZdgZy)z"Image processor class for Swin2SR.N)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) ImagesKwargs) TensorTypefilter_out_non_signature_kwargsloggingceZdZUeed<y)Swin2SRImageProcessorKwargs size_divisorN)__name__ __module__ __qualname__int__annotations__f/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/swin2sr/image_processing_swin2sr.pyrr%srrF)totalc2eZdZdZdgZeZ ddedee zdededdf fd Z dd e jd ed e ezdzd e ezdzfdZedddddej"dfdededzde dzdedzdedzde ezdzd e ezd e ezdzfdZxZS)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_values do_rescalerescale_factordo_padrreturnNc t|di|||_||_||_|j d}|||_y||_y)Npad_sizer)super__init__r$r%r&getr)selfr$r%r&rkwargsr) __class__s rr+zSwin2SRImageProcessor.__init__9sM "6"$, ::j),8,DL(rimagesize 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)moder2r3)rr) r-r0r1r2r3 old_height old_width pad_height pad_widths rrzSwin2SRImageProcessor.padIsq:!/u6G H I D(1,4zA $&*d2Y>  _q)n -#/   rimagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}t |}t |s t dt|||D cgc] } t| }} |r#t|drtjd|t|d}|r!|D cgc]} |j| ||}} |r!|D cgc]} |j| ||}} |D cgc]} t| ||}} d|i} t!| | Scc} wcc} wcc} wcc} w) 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.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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. zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)r$r%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.)r0scaler3)r1r3)input_channel_dimr#)data tensor_type)r$r%r&rr r ValueErrorrrr logger warning_oncer rescalerrr) r-r<r$r%r&rr=r2r3r0rAs r preprocessz Swin2SRImageProcessor.preprocessrszX$.#9Zt +9+E4K^K^!-4;;'3'?|TEVEV )&1F#rs s%!) 6<vay I  $ 5Rc dF kqrbgdhhuBB5= s s3D.D3%D8D=)Tgp?T)NN)rrr__doc__model_input_namesr valid_kwargsboolrfloatr+npndarraystrr rrFIRSTr rrG __classcell__)r/s@rr"r")st ((.L &- SSe S S  S S(6:;? ' zz' ' ++d2 ' !11D8 ' R%&#''+"#'26.>.D.D;?TCTC4KTC TC t TC Dj TCj(4/TC++TC!11D8TC'TCrr")rInumpyrNimage_processing_utilsrrimage_transformsrrr image_utilsr r r r r rrrprocessing_utilsrutilsrrr get_loggerrrDrr"__all__rrrr[sn)FPP   -II   H %,e^C.^CB # #r