o iV@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z dd l!m"Z"m#Z#e $e%Z&e"r`ddl'Z'e#d d Gd d d eZ(d gZ)dS)z Image processor class for Donut.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizepadresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)is_vision_availablerequires)vision)backendsc%seZdZdZdgZddejddddddddf dedee e e fd ed ed ed ed ede e e fdedee e ee fdee e ee fddffdd Z  d%dejde e e fdee e efdee e efdejf ddZ   d&dejde e e fdedee e efdee e efdejf ddZejddfdejde e e fd edee e efdee e efdejf ddZejddfdejde e e fd edee e efdee e efdejf dd Zedddddddddddddejdfd!edeedee e e fd eed eed eed eeded eedee deedee e ee fdee e ee fd"ee e efdeedee e efdejjf"d#d$ZZS)'DonutImageProcessora Constructs a Donut image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by `do_resize` in the `preprocess` method. size (`dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`): Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method. do_thumbnail (`bool`, *optional*, defaults to `True`): Whether to resize the image using thumbnail method. do_align_long_axis (`bool`, *optional*, defaults to `False`): Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image. If `random_padding` is set to `True` in `preprocess`, each image is padded with a random amount of padding on each size, up to the largest image size in the batch. Otherwise, all images are padded to the largest image size in the batch. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by `do_rescale` 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 `rescale_factor` in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by `do_normalize` 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`): Image standard deviation. pixel_valuesTNFgp? do_resizesizeresample do_thumbnaildo_align_long_axisdo_pad do_rescalerescale_factor do_normalize image_mean image_stdreturnc  stjdi| |dur|nddd}t|ttfr"|ddd}t|}||_||_||_||_ ||_ ||_ ||_ ||_ | |_| durG| nt|_| durS| |_dSt|_dS)Ni i)heightwidth)super__init__ isinstancetuplelistrr"r#r$r%r&r'r(r)r*r r+rr,) selfr"r#r$r%r&r'r(r)r*r+r,kwargs __class__r1d/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/donut/image_processing_donut.pyr3^s zDonutImageProcessor.__init__image data_formatinput_data_formatc Cst||d\}}|d|d}}|durt|}|tjkr!d} n|tjkr)d} ntd|||kr8||ks@||krH||krHtj|d| d }|durSt|||d }|S) a Align the long axis of the image to the longest axis of the specified size. Args: image (`np.ndarray`): The image to be aligned. size (`dict[str, int]`): The size `{"height": h, "width": w}` to align the long axis to. data_format (`str` or `ChannelDimension`, *optional*): The data format of the output image. If unset, the same format as the input image is used. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Returns: `np.ndarray`: The aligned image.  channel_dimr.r/N)r)rAzUnsupported data format: r)axesinput_channel_dim) rrrLASTFIRST ValueErrornprot90r ) r7r<r#r=r> input_height input_width output_height output_widthrot_axesr1r1r;align_long_axiss  z#DonutImageProcessor.align_long_axisrandom_paddingcCs|d|d}}t||d\}} || } ||} |r0tjjd| dd} tjjd| dd} n| d} | d} | | }| | }| |f| |ff}t||||dS) a Pad the image to the specified size. Args: image (`np.ndarray`): The image to be padded. size (`dict[str, int]`): The size `{"height": h, "width": w}` to pad the image to. random_padding (`bool`, *optional*, defaults to `False`): Whether to use random padding or not. data_format (`str` or `ChannelDimension`, *optional*): The data format of the output image. If unset, the same format as the input image is used. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. r.r/r?rrA)lowhighrBr=r>)rrIrandomrandintr )r7r<r#rQr=r>rMrNrKrL delta_width delta_heightpad_toppad_left pad_bottom pad_rightpaddingr1r1r; pad_imageszDonutImageProcessor.pad_imagec Kst||d\}}|d|d} } t|| } t|| } | |kr%| |kr%|S||kr2t|| |} n ||kr>t|| |} t|f| | f|d||d|S)as Resize the image to make a thumbnail. The image is resized so that no dimension is larger than any corresponding dimension of the specified size. Args: image (`np.ndarray`): The image to be resized. size (`dict[str, int]`): The size `{"height": h, "width": w}` to resize the image to. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): The resampling filter to use. data_format (`Optional[Union[str, ChannelDimension]]`, *optional*): The data format of the output image. If unset, the same format as the input image is used. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. r?r.r/g@)r#r$ reducing_gapr=r>)rminintr ) r7r<r#r$r=r>r8rKrLrMrNr.r/r1r1r; thumbnails*  zDonutImageProcessor.thumbnailc KsHt|}t|d|d}t||d|d}t|f||||d|} | S)a Resizes `image` to `(height, width)` specified by `size` using the PIL library. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. r.r/F)r#default_to_squarer>)r#r$r=r>)rr`r r ) r7r<r#r$r=r>r8 shortest_edge output_size resized_imager1r1r;r s zDonutImageProcessor.resizeimagesreturn_tensorsc s0|dur|nj}durnjtttfr dddtdur*nj|dur3|nj}|dur<|nj}|durE|nj }| durN| nj } durWnj | dur`| nj } durinj durrnjt|}t|stdt| | |ddd|D}dd|D}| rt|drtd durt|d|rfd d|D}|r͇fd d|D}|rڇfd d|D}|rfd d|D}| rfdd|D}| rfdd|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`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`dict[str, int]`, *optional*, defaults to `self.size`): Size of the image after resizing. Shortest edge of the image is resized to min(size["height"], size["width"]) with the longest edge resized to keep the input aspect ratio. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only has an effect if `do_resize` is set to `True`. do_thumbnail (`bool`, *optional*, defaults to `self.do_thumbnail`): Whether to resize the image using thumbnail method. do_align_long_axis (`bool`, *optional*, defaults to `self.do_align_long_axis`): Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. do_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image. If `random_padding` is set to `True`, each image is padded with a random amount of padding on each size, up to the largest image size in the batch. Otherwise, all images are padded to the largest image size in the batch. random_padding (`bool`, *optional*, defaults to `self.random_padding`): Whether to use random padding when padding the image. If `True`, each image in the batch with be padded with a random amount of padding on each side up to the size of the largest image in the batch. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image pixel values. 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 for normalization. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use for normalization. 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: defaults to 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. Nr0zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r(r)r*r+r,r"r#r$cSg|]}t|qSr1)r.0r<r1r1r; z2DonutImageProcessor.preprocess..cSrir1)rrjr1r1r;rlrmrzIt 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#r>)rPrjr>r7r#r1r;rlcg|] }j|dqS))r<r#r$r>)r rj)r>r$r7r#r1r;rlcrn))r<r#r>)rbrjror1r;rlrpcrq))r<r#rQr>)r^rj)r>rQr7r#r1r;rls csg|] }j|dqS))r<scaler>)rescalerj)r>r)r7r1r;rlscsg|] }j|dqS))r<meanstdr>) normalizerj)r+r,r>r7r1r;rlrrcsg|] }t|dqS)rD)r rjrTr1r;rlsr!)data tensor_type)r"r#r4r5r6rr$r%r&r'r(r)r*r+r,rrrHrrlogger warning_oncerr)r7rgr"r#r$r%r&r'rQr(r)r*r+r,rhr=r>rxr1) r=r+r,r>rQr$r)r7r#r; preprocess3s|K    zDonutImageProcessor.preprocess)NN)FNN) __name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrrarfloatr6r3rIndarrayrrPr^BICUBICrbr rrGrrPILImager| __classcell__r1r1r9r;r 6s.$    '  3  .  6  '     r )*rtypingrrnumpyrIimage_processing_utilsrrrimage_transformsrr r r r image_utilsr rrrrrrrrrrrutilsrrrutils.import_utilsrr get_loggerr}rzrr __all__r1r1r1r;s"8  #