o Zh4@sdZddlmZmZmZddlZddlmZm Z ddl m Z m Z ddl mZmZmZmZmZmZmZmZmZmZmZddlmZmZmZeeZGd d d eZ d gZ!dS) 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_kwargsloggingcsneZdZdZdgZ       ddedeeefd ed e eee efd e eee efd ed eddffdd Z   dde j d ede eeefde eeefde j f ddZeddddddddejdf dedede ede ed e ed e eee efd e eee efd e ed e ede eeefdeeefde eeeffddZZS)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_valuesTp?N do_rescalerescale_factor do_normalize image_mean image_stddo_padsize_divisibilityreturnc  sXtjdi|||_||_||_||_|dur|nt|_|dur$|nt|_ ||_ dS)N) super__init__rrr!rr rr r r") selfrrrrr r!r"kwargs __class__r$e/var/www/auris/lib/python3.10/site-packages/transformers/models/vitmatte/image_processing_vitmatte.pyr&Gs  zVitMatteImageProcessor.__init__image data_formatinput_data_formatc Cs|durt|}t||\}}||dkrdn|||}||dkr%dn|||}||dkrAd|fd|ff} t|| ||d}|durKt|||}|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)paddingr-r.)rrrr ) r'r,r"r-r.heightwidthZ pad_heightZ pad_widthr/r$r$r+ pad_image[s  z VitMatteImageProcessor.pad_imageimagestrimapsreturn_tensorsc  s|dur|nj}|dur|nj}|dur|nj}dur!njdur*njdur3njdur<njt|}t|dd}t|sQt dt|sYt dt |||ddd|D}d d|D}|rt |d rt d durt|d |rfd d|D}fd d|D}|rfdd|D}tjkrdnd fddt||D}|rчfdd|D}fdd|D}d|i} t| | dS)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. N)Zexpected_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"cSg|]}t|qSr$r.0r,r$r$r+ z5VitMatteImageProcessor.preprocess..cSr7r$r8r:trimapr$r$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.cg|] }j|dqS)r,scaler.Zrescaler9r.rr'r$r+r;cr?r@rBr=rCr$r+r;rDcsg|] }j|dqS))r,meanZstdr.) normalizer9)rr r.r'r$r+r;scs,g|]\}}tj|tj|dgdqS)axis)npZ concatenateZ expand_dims)r:r,r>rHr$r+r;scsg|] }j|dqS))r"r.)r2r9)r.r'r"r$r+r;rDcsg|] }t|dqS))r,Z channel_dimZinput_channel_dim)r r9)r-r.r$r+r; s r)dataZ tensor_type)rrr!rrr r"rr ValueErrorrrloggerZ warning_oncerr ZLASTzipr)r'r3r4rrrrr r!r"r5r-r.rKr$)rIr-rr r.rr'r"r+ preprocessst:      z!VitMatteImageProcessor.preprocess)TrTNNTr)rNN)__name__ __module__ __qualname____doc__Zmodel_input_namesboolrintfloatrrr&rJZndarraystrr r2rZFIRSTr rrO __classcell__r$r$r)r+r*s   )     r)"rStypingrrrnumpyrJZimage_processing_utilsrrZimage_transformsrr Z image_utilsr r r r rrrrrrrutilsrrrZ get_loggerrPrMr__all__r$r$r$r+s4  i