`i\7dZddlmZmZddlZddlmZmZddl m Z m Z ddl m Z mZmZmZmZmZmZmZmZmZmZddlmZmZmZdd lmZejeZ Gd d eZ!d gZ"dS) z#Image processor class for ViTMatte.)OptionalUnionN)BaseImageProcessor BatchFeature)padto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)deprecate_kwargceZdZdZdgZ ddedeeefd ed e eee efd e eee efd ed eddffd Z e dZ e jdZ ddejdede eeefde eeefdejf dZeeddd ddddddddejdf dedede ede ed e ed e eee efd e eee efd e ed e ede eeefdeeefde eeeffdZxZS)VitMatteImageProcessora Constructs a ViTMatte 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. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to make the width and height divisible by `size_divisor`. Can be overridden by the `do_pad` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to 32): The width and height of the image will be padded to be divisible by this number. pixel_valuesTp?N do_rescalerescale_factor do_normalize image_mean image_stddo_pad size_divisorreturnc tjdi|||_||_||_||_||nt |_||nt|_ | d} | | n||_ dS)Nsize_divisibility) super__init__rr r#rr r!r r"getr$) selfrrr r!r"r#r$kwargsr' __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/vitmatte/image_processing_vitmatte.pyr*zVitMatteImageProcessor.__init__Hs ""6"""$( ,(2(>**DZ&/&;AV"JJ':;;1B1N--T`cDtd|jSNzk`self.size_divisibility` attribute is deprecated and will be removed in v5. Use `self.size_divisor` insteadloggerwarningr$)r,s r/r'z(VitMatteImageProcessor.size_divisibility]s& y     r0cHtd||_dSr2r3)r,values r/r'z(VitMatteImageProcessor.size_divisibilityds+ y   "r0imager' data_formatinput_data_formatc|t|}t||\}}||zdkrdn|||zz }||zdkrdn|||zz }||zdkrd|fd|ff} t|| ||}|t|||}|S)a Args: image (`np.ndarray`): Image to pad. size_divisibility (`int`, *optional*, defaults to 32): The width and height of the image will be padded to be divisible by this number. 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. Nr)paddingr9r:)rrrr ) r,r8r'r9r:heightwidth pad_height pad_widthr<s r/ pad_imagez VitMatteImageProcessor.pad_imageks2  $ >u E E &u.?@@  #4499QQ?PSY\mSm?m !22a77AA=NQVYjQj=j z !A % %:I7GwK[lmmmE  "/{DUVVE r0v5)versionnew_nameimagestrimapsreturn_tensorsc  ||nj}||nj}||nj}njnjnj  nj t|}t|d}t|stdt|stdt||d|D}d|D}|r/t|d rt d  t|d  |r fd |D} fd |D}|r fd |D} tjkrdnd fdt#||D}|r fd|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`. trimaps (`ImageInput`): Trimap to preprocess. 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_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`): Image mean to use if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use if `do_normalize` is set to `True`. do_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image. size_divisor (`int`, *optional*, defaults to `self.size_divisor`): The size divisibility to pad the image to if `do_pad` is set to `True`. 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: - `"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. N)expected_ndimszlInvalid trimap type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rrr r!r"c,g|]}t|Sr(r).0r8s r/ z5VitMatteImageProcessor.preprocess..s <<.s @@@f>&))@@@r0rzIt 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.c@g|]}|S)r8scaler:rescale)rMr8r:rr,s r/rNz5VitMatteImageProcessor.preprocess..s< 5Rc ddr0c@g|]}|SrRrT)rMrPr:rr,s r/rNz5VitMatteImageProcessor.preprocess..s< 6Sd eer0cBg|]}|S))r8meanstdr:) normalize)rMr8r!r"r:r,s r/rNz5VitMatteImageProcessor.preprocess..s>U^oppr0c ng|]1\}}tj|tj|g2S))axis)np concatenate expand_dims)rMr8rPr]s r/rNz5VitMatteImageProcessor.preprocess.. sP   v NE2>&t#D#D#DED Q Q Q   r0c@g|]}|S))r'r:)rA)rMr8r:r,r$s r/rNz5VitMatteImageProcessor.preprocess..s<u Xijjr0c4g|]}t|S))r8 channel_diminput_channel_dim)r )rMr8r9r:s r/rNz5VitMatteImageProcessor.preprocess..s9    (e`q r r r   r0r)data tensor_type)rr r#rr!r"r$rr ValueErrorrrr4 warning_oncerr LASTzipr)r,rErFrrr r!r"r#r$rGr9r:rer]s` ` `` ` `` @r/ preprocessz!VitMatteImageProcessor.preprocesssv$.#9ZZt '3'?||TEV !-4;+9+E4K^#-#9ZZt !*!6IIDN '3'?||TEV )&11*71EEEG$$ :  F## :  &!)%!     =vay I I   #F%G  #F '*:*???rrQ    !$VW!5!5     #F          '>BBBBr0)TrTNNTr)rNN)__name__ __module__ __qualname____doc__model_input_namesboolrintfloatrlistr*propertyr'setterr^ndarraystrr rArrFIRSTr rrk __classcell__)r.s@r/rr+s 4(( ,3!:>9=aaac5j)a a U5$u+#567 a E%e"456 aaa aaaaaa*!!X! """"$>BDH ''z''eC)9$9:; ' $E#/?*?$@A '  ''''R%$&&_($PPP &**.'+:>9=!%&*;?4D4JDHHCHCHCHCTN HC ! HC tn HCU5$u+#567HCE%e"456HCHCsmHC!sJ!78HC3 001HC$E#/?*?$@AHCHCHCQP'&HCHCHCHCHCr0r)#rotypingrrnumpyr^image_processing_utilsrrimage_transformsrr image_utilsr r r r rrrrrrrutilsrrrutils.deprecationr get_loggerrlr4r__all__r(r0r/rst*)""""""""FFFFFFFF@@@@@@@@                          JIIIIIIIII000000  H % %sCsCsCsCsC/sCsCsCl $ $r0