rh(>dZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZej@e!Z"erddl#Z#Gd d eZ$d gZ%y) zImage processor class for BiT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc#eZdZdZdgZddej ddddddddf dedee e e fded ed ee e e fd ed e e e fd edee e ee fdee e ee fdeddffd Zej ddfdej"de e e fdedee e efdee e efdej"f dZeddddddddddddej*dfdedeedee e e fded eed ee d eed ee d eedee e ee fdee e ee fdeedee e efdeedee e efdej2j2f dZxZS)BitImageProcessora` Constructs a BiT 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 `PILImageResampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image to the specified `crop_size`. Can be overridden by `do_center_crop` in the `preprocess` method. crop_size (`dict[str, int]` *optional*, defaults to 224): Size of the output image after applying `center_crop`. Can be overridden by `crop_size` in the `preprocess` method. 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: Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `OPENAI_CLIP_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 `OPENAI_CLIP_MEAN`): 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. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  6t |d i| ||nddi}t|d}||nddd}t|dd}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_y) N shortest_edgeF)default_to_square)heightwidthTr#)r. param_name)super__init__rrr r!r"r#r$r%r&r r'rr(r))selfrr r!r"r#r$r%r&r'r(r)kwargs __class__s /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/bit/image_processing_bit.pyr4zBitImageProcessor.__init__\s "6"'tos-CTU;!*!6IsUX*DT&/&;,image data_formatinput_data_formatc d}d|vr|d}d}nd|vrd|vr |d|df}n tdt||||}t|f||||d|S) aZ Resize an image. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. 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. Tr,Fr/r0zASize must contain either 'shortest_edge' or 'height' and 'width'.)r r.r<)r r!r;r<) ValueErrorr r ) r5r:r r!r;r<r6r. output_sizes r8r zBitImageProcessor.resize~s2! d "(D %   'T/NDM2D`a a2 //    #/     r9imagesreturn_tensorsc 2||n |j}||n |j}t|dd}||n |j}||n |j}||n |j }t|dd}||n |j }||n |j}| | n |j} | | n |j} | | n |j} | | n |j} t|}t|s tdt||| | | ||||| | r|Dcgc] }t!|}}|Dcgc] }t#|}}|r#t%|drt&j)d |t+|d}g}|D]m}|r|j-|||| }|r|j/||| }|r|j1||| }| r|j3|| | | }|j5|o|Dcgc]}t7|||}}d|i}t9|| Scc}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`. 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 size["shortest_edge"], 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_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image. crop_size (`dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the center crop. Only has an effect if `do_center_crop` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image. 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. Only has an effect if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. 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. r F)r1r.r#TzkInvalid 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#rr 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:r r!r<)r:r r<)r:scaler<)r:meanstdr<)input_channel_dimr)data tensor_type)rr rr!r"r#r$r%r&r'r(r)rrr>rr rrlogger warning_oncerr center_croprescale normalizeappendr r)r5r@rr r!r"r#r$r%r&r'r(r)rAr;r<r: all_imagesrGs r8 preprocesszBitImageProcessor.preprocessszL"+!6IDNN 'tTYYTfN'38+9+E4K^K^!*!6IDNN !) W[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^$V,F#:  &!)%!)  9?@nU+@F@6<vay I   %E %dXar s((u9Xi(j 5Zk ljiSd'   e $ %&$  ({N_ `  '>BBOA=< s H !H"H)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrintrfloatlistr4npndarrayrr rFIRSTrrPILImagerP __classcell__)r7s@r8rr3s $L(()-'9'A'A#.2,3!:>9=#--tCH~&-% -  - DcN+ --c5j)--U5$u+#567-E%e"456-- -L(:'A'A>BDH / zz/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / b%&%))-'+)-#'%)*.'+:>9=)-;?2B2H2HDH!QCQCD>QCtCH~& QC % QC ! QCC=QCTNQC!QCtnQCU5$u+#567QCE%e"456QC!QC!sJ!78QC./QC $E#/?*?$@A!QC" #QC'QCr9r)&rTtypingrrnumpyr]image_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrutilsrrrr get_loggerrQrIr`r__all__r2r9r8rksx%"UU    _^   H %NC*NCb  r9