qi3dZddlZddlmZmZddlmZmZddl m Z m Z m Z m Z mZmZmZmZmZmZmZddlmZddlmZmZmZej6eZGd d ed ZGd deZdgZ y)z#Image processor class for ViTMatte.N)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) ImagesKwargs) TensorTypefilter_out_non_signature_kwargsloggingceZdZUeed<y)VitMatteImageProcessorKwargs size_divisorN)__name__ __module__ __qualname__int__annotations__h/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/vitmatte/image_processing_vitmatte.pyrr(sr rF)totalceZdZdZdgZeZ ddedee zdede e e zdzde e e zdzd ed ed dffd Z dd e jd edeezdzdeezdzd e jf dZeddddddddej$df dedededzde dzdedzde e e zdzde e e zdzd edzd edzdeezdzdeezdeezdzfdZxZS)VitMatteImageProcessora Constructs a ViTMatte image processor. Args: do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to make the width and height divisible by `size_divisor`. Can be overridden by the `do_pad` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to 32): The width and height of the image will be padded to be divisible by this number. pixel_valuesN do_rescalerescale_factor do_normalize image_mean image_stddo_padrreturnc t |di|||_||_||_||_||nt |_||nt|_ |jd} | | |_ y||_ y)Nsize_divisibilityr) super__init__r&r(r+r'rr)r r*getr) selfr&r'r(r)r*r+rkwargsr. __class__s r!r0zVitMatteImageProcessor.__init__Jsw "6"$( ,(2(>*DZ&/&;AV"JJ':;1B1N-T`r image data_formatinput_data_formatc| t|}t||\}}||zdk(rdn|||zz }||zdk(rdn|||zz }||zdkDrd|fd|ff} t|| ||}| t|||}|S)a  Args: image (`np.ndarray`): Image to pad. size_divisor (`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. r)paddingr6r7)r r rr) r2r5rr6r7heightwidth pad_height pad_widthr9s r! pad_imagez VitMatteImageProcessor.pad_image_s2  $ >u E &u.?@  </14Q,R^I^:^ -2A u|G[8[ z !A %:I7GwK[lmE  "/{DUVE r imagestrimapsreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } t|}t|d}t|s tdt|s tdt||||||D cgc] } t| }} |Dcgc] }t|}}|r#t|drtjd| t|d} |rB|D cgc]} |j!| || }} |Dcgc]}|j!||| }}|r"|D cgc]} |j#| ||| }} | t$j&k(rd nd}t)||D cgc]3\} }t+j,| t+j.|| g| 5}} }|r!|D cgc]} |j1| | | }} |D cgc]} t3| | | }} d|i}t5|| Scc} wcc}wcc} wcc}wcc} 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`. 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.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. )expected_ndimszTInvalid trimap type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.TensorzSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)r&r'r(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.)r5scaler7)r5meanstdr7)axis)rr7)r5 channel_diminput_channel_dimr%)data tensor_type)r&r(r+r'r)r*rrr ValueErrorrrrlogger warning_oncer rescale normalizer LASTzipnp concatenate expand_dimsr>rr)r2r?r@r&r'r(r)r*r+rrAr6r7r5trimaprIrLs r! preprocessz!VitMatteImageProcessor.preprocesssp$.#9Zt '3'?|TEVEV !-4;;+9+E4K^K^#-#9Zt !*!6IDNN '3'?|TEVEV )&1*71EG$st tF#rs s%!)%!  6<&)@@ /&)4   s   $ >vay I  $ 5Rc dF & 6Sd eG $U^opF '*:*?*??rQ"%VW!5 v NNE2>>&t#DED Q  $uBBa=@    s0 I!I0I I4I88I9I!I&)Tgp?TNNT )rZNN)rrr__doc__model_input_namesr valid_kwargsboolrfloatlistr0rUndarraystrr r>rFIRSTr rrY __classcell__)r4s@r!r$r$,s$4((/L &-!1504aae a a DK'$. a 4;&- aaa a059;? 'zz''++d2 ' !11D8 '  'R%& #''+$(1504"#'26.>.D.D;?@C@C@C4K @C  @C Tk @CDK'$.@C4;&-@Ct @CDj@Cj(4/@C++@C!11D8@C'@Cr r$)!r[numpyrUimage_processing_utilsrrimage_transformsrr image_utilsrr r r r r rrrrrprocessing_utilsrutilsrrr get_loggerrrOrr$__all__rr r!rmsp*F@    -II   H %