`iCEdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZej e!Z"erddl#Z#Gd d eZ$d gZ%dS) z"Image processor class for TextNet.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availableloggingc$NeZdZdZdgZdddejdddddeedf de d e e e e fd e d ed e d e e e e fde dee efde de eeeefde eeeefde ddffd Zejddfdejd e e e fd ede ee efde ee efdejf dZdddddddddddddejdfdede e d e e e e fd e e d e ed e e d e e de e de ede e de eeeefde eeeefde e de ee efde ede ee efdejjf"dZxZS)TextNetImageProcessora( Constructs a TextNet 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": 640}`): 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. size_divisor (`int`, *optional*, defaults to 32): Ensures height and width are rounded to a multiple of this value after resizing. 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_center_crop (`bool`, *optional*, defaults to `False`): 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 (`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 `[0.485, 0.456, 0.406]`): 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 `[0.229, 0.224, 0.225]`): 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_valuesTN Fgp? do_resizesize size_divisorresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  ~tjd i| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | |_ | | nt|_ | | nt|_| |_gd |_dS) N shortest_edgeiF)default_to_square)heightwidthr%) param_name)imagesr r!r"r#r$r%r&r'r(r)r*r+return_tensors data_formatinput_data_format)super__init__rr r!r"r#r$r%r&r'r(r r)rr*r+_valid_processor_keys)selfr r!r"r#r$r%r&r'r(r)r*r+kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/textnet/image_processing_textnet.pyr:zTextNetImageProcessor.__init__^s ""6"""'ttos-CTU;;;!*!6IIsUX**DY&/&;AU,& & & """imager6r7c Ld|vr |d}n(d|vrd|vr|d|df}ntdt|||d\}}||jzdkr||j||jzz z }||jzdkr||j||jzz z }t|f||f|||d|S) a Resize an image. The shortest edge of the image is resized to size["shortest_edge"] , with the longest edge resized to keep the input aspect ratio. Both the height and width are resized to be divisible by 32. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. size_divisor (`int`, *optional*, defaults to `32`): Ensures height and width are rounded to a multiple of this value after resizing. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. default_to_square (`bool`, *optional*, defaults to `False`): The value to be passed to `get_size_dict` as `default_to_square` when computing the image size. If the `size` argument in `get_size_dict` is an `int`, it determines whether to default to a square image or not.Note that this attribute is not used in computing `crop_size` via calling `get_size_dict`. r.r1r2zASize must contain either 'shortest_edge' or 'height' and 'width'.F)r!r7r/r)r!r#r6r7) ValueErrorr r"r ) r<rAr!r#r6r7r=r1r2s r?r zTextNetImageProcessor.resizes > d " "(DD   'T//NDM2DD`aa a4 0AUZ    D% % * * d'6D4E+EF FF 4$ $ ) ) T&%$2C*CD DE  %#/       r@r4r5c J||n|j}||n|j}t|dd}||n|j}||n|j}||n|j}||n|j}t|dd}||n|j}| | n|j} | | n|j } | | n|j } | | n|j } | | n|j } t||jt!|}t#|st%dt'|| | | | ||||| | r d |D}d |D}t)|d r|rt*d t/|d g}|D]}|r||||}|r|||}|r||| }| r||| | }||fd|D}d|i}t;||S)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. size_divisor (`int`, *optional*, defaults to `32`): Ensures height and width are rounded to a multiple of this value after resizing. 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. Nr!F)r3r/r%T)captured_kwargsvalid_processor_keyszkInvalid 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 r!r#c,g|]}t|Sr8)r .0rAs r? z4TextNetImageProcessor.preprocess..:s @@@nU++@@@r@c,g|]}t|Sr8)rrHs r?rJz4TextNetImageProcessor.preprocess..=s <<.Zs9    ({N_ ` ` `   r@r)data tensor_type)r r!rr"r#r$r%r&r'r(r)r*r+rkeysr;rrrCrrlogger warning_oncerr center_croprescale normalizeappendr)r<r4r r!r"r#r$r%r&r'r(r)r*r+r5r6r7r= all_imagesrArQs `` r? preprocessz TextNetImageProcessor.preprocesssR"+!6IIDN 'ttTYTfNNN'3'?||TEV '388+9+E4K^!*!6IIDN !) W[\\\ #-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN +9+E4K^ DLfgggg)&11F## :  &!)%!)   A@@@@@F=vay I I   % %E t %dXar ss k((u9Xi(jj m 5Zk ll jiSd'   e $ $ $ $     #    '>BBBBr@)__name__ __module__ __qualname____doc__model_input_namesrBILINEARr rboolrdictstrintrfloatlistr:npndarrayrr FIRSTrrPILImager[ __classcell__)r>s@r?rr3s&&P(()-'9'B$.2,3!:O9M#4 4 4 tCH~&4  4 % 4  4 DcN+4 4 c5j)4 4 U5$u+#5674 E%e"4564 4  4 4 4 4 4 4 t(:'B>BDH 5 5 z5 38n5 % 5 eC)9$9:; 5 $E#/?*?$@A 5  5 5 5 5 t%))-&*15)-#'%)*.'+:>9=)-;?2B2HDH#UCUCUCD>UCtCH~& UC sm UC -. UC!UCC=UCTNUC!UCtnUCU5$u+#567UCE%e"456UC!UC!sJ!78UC ./!UC"$E#/?*?$@A#UC& 'UCUCUCUCUCUCUCUCr@r)&r_typingrrnumpyrhimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrrutilsrrr get_loggerr\rTrkr__all__r8r@r?rvs)(""""""""UUUUUUUUUU                            >=========  H % %JJJmCmCmCmCmC.mCmCmC` # #r@