o iCE@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZe e!Z"erVddl#Z#Gd d d eZ$d gZ%dS) z"Image processor class for TextNet.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availableloggingc$seZdZdZdgZdddejdddddeedf de d e e e e fd e d ed e d e e e e fde dee efde de eeeefde eeeefde ddffdd Zejddfdejd e e e fd ede ee efde ee efdejf ddZdddddddddddddejdfdede 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"ddZZS) 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  stjd i| |dur|nddi}t|dd}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ | |_ | durK| nt |_ | durT| nt|_| |_gd |_dS) N shortest_edgeiF)default_to_square)heightwidthr#) param_name)imagesrrr r!r"r#r$r%r&r'r(r)return_tensors data_formatinput_data_format)super__init__rrrr r!r"r#r$r%r&r r'r r(r)_valid_processor_keys)selfrrr r!r"r#r$r%r&r'r(r)kwargs __class__r5h/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/textnet/image_processing_textnet.pyr7^s$  zTextNetImageProcessor.__init__imager3r4c Ksd|vr |d}nd|vrd|vr|d|df}ntdt|||dd\}}||jdkr9||j||j7}||jdkrJ||j||j7}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+r.r/zASize must contain either 'shortest_edge' or 'height' and 'width'.F)rr4r,r)rr!r3r4) ValueErrorr r r ) r9r>rr!r3r4r:r.r/r5r5r=r s,  zTextNetImageProcessor.resizer1r2c s|dur|n|j}|dur|n|j}t|ddd}|dur|n|j}|dur(|n|j}|dur1|n|j}|dur:|n|j}t|ddd}|durJ|n|j}| durS| n|j} | dur\| n|j } | dure| n|j } | durn| n|j } | durw| n|j } t ||jdt|}t|stdt|| | | | |||||d | rd d |D}d d |D}t|d r|rtddurt|d g}|D]1}|r|j|||d}|r|j||d}|r|j|| d}| r|j|| | d}||qȇfdd |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 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. NrF)r0r,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$r%r&r'r(r"r#rrr!cSg|]}t|qSr5)r.0r>r5r5r= :z4TextNetImageProcessor.preprocess..cSrBr5)rrCr5r5r=rE=rFrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r>rr!r4)r>rr4)r>scaler4)r>meanstdr4csg|] }t|dqS))input_channel_dim)r rCr3r4r5r=rEZs r)data tensor_type)rrrr r!r"r#r$r%r&r'r(r)rkeysr8rrr?rrlogger warning_oncerr center_croprescale normalizeappendr)r9r1rrr r!r"r#r$r%r&r'r(r)r2r3r4r: all_imagesr>rLr5rKr= preprocesssvI     z TextNetImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBILINEARr r boolrdictstrintrfloatlistr7npndarrayrr FIRSTrrPILImagerV __classcell__r5r5r;r=r3s(     :  :     r)&rZtypingrrnumpyrcimage_processing_utilsrrrimage_transformsrr r r image_utilsr r rrrrrrrrrrutilsrrr get_loggerrWrOrfr__all__r5r5r5r=s8  2