sgz4dZddlmZmZmZddlZddlmZm Z ddl m Z m Z ddl mZmZmZmZmZmZmZmZmZmZmZddlmZmZmZej:eZGd d eZ y) z#Image processor class for ViTMatte.)ListOptionalUnionN)BaseImageProcessor BatchFeature)padto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingceZdZdZdgZ ddedeeefdede eee efde eee efd ed ed dffd Z dd e jd ede eeefde eeefd e jf dZeddddddddej$df dedede ede ede ede eee efde eee efd e ed e ede eeefdeeefde eeeffdZxZS)VitMatteImageProcessora Constructs a ViTMatte image processor. Args: do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to make the width and height divisible by `size_divisibility`. Can be overridden by the `do_pad` parameter in the `preprocess` method. size_divisibility (`int`, *optional*, defaults to 32): The width and height of the image will be padded to be divisible by this number. pixel_valuesN do_rescalerescale_factor do_normalize image_mean image_stddo_padsize_divisibilityreturnc t |di|||_||_||_||_||nt |_||nt|_ ||_ y)N) super__init__rrr!rr rr r r") selfrrrrr r!r"kwargs __class__s i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/vitmatte/image_processing_vitmatte.pyr'zVitMatteImageProcessor.__init__GsY "6"$( ,(2(>*DZ&/&;AV!2image 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_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. r)paddingr.r/)rrr r ) r(r-r"r.r/heightwidth pad_height pad_widthr1s r+ pad_imagez VitMatteImageProcessor.pad_image[s2  $ >u E &u.?@  #449Q?PSY\mSm?m !22a7A=NQVYjQj=j 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|}}t|dr|rtjd| t|d} |rB|D cgc]} |j!| || }} |Dcgc]}|j!||| }}|r"|D cgc]} |j#| ||| }} t%||D cgc]3\} }t'j(| t'j*|d gd 5}} }|r!|D cgc]} |j-| | | }} |D cgc]} t/| | | }} d|i}t1|| 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_divisibility (`int`, *optional*, defaults to `self.size_divisibility`): 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. )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.)rrrrr 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.)r-scaler/)r-meanstdr/)axis)r"r/)r- channel_diminput_channel_dimr)data tensor_type)rrr!rrr r"rr ValueErrorrrrlogger warning_oncerrescale normalizezipnp concatenate expand_dimsr6r r)r(r7r8rrrrr r!r"r9r.r/r-trimaprDs r+ preprocessz!VitMatteImageProcessor.preprocessst$.#9Zt '3'?|TEVEV !-4;;+9+E4K^K^#-#9Zt !*!6IDNN 1B1N-TXTjTj$V,%ga@G$:  F#:  &!)%!/ 6<&)@@ 6!9 %*   s   $ >vay I  $ 5Rc dF & 6Sd eG $U^opFdggmovcw R_RWY_BNNE2>>&r#BC" M   $u8I]noF   (e`q r  '>BB]=@     s0 H-#H22H7H<6I#8I$I I)Tgp?TNNT )rQNN)__name__ __module__ __qualname____doc__model_input_namesboolrintfloatrrr'rLndarraystrr r6rFIRSTrrrP __classcell__)r*s@r+rr*sG4(( ,3!:>9=!#33c5j)3 3 U5$u+#567 3 E%e"456 333 3."$>BDH 'zz''eC)9$9:; ' $E#/?*?$@A '  'R%& &**.'+:>9=!%+/;?4D4J4JDHHCHCHCTN HC ! HC tn HCU5$u+#567HCE%e"456HCHC$C=HC!sJ!78HC3 001HC$E#/?*?$@AHC'HCr,r)!rUtypingrrrnumpyrLimage_processing_utilsrrimage_transformsr r image_utilsr r r rrrrrrrrutilsrrr get_loggerrRrGrr%r,r+res[*((F@    JI   H %cC/cCr,