`i; dZddlmZmZddlZddlmZmZm Z ddl m Z m Z ddl mZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd lmZerddl Z ej!e"Z#ed Gd d eZ$d gZ%dS)zImage processor class for DeiT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requires)vision)backendsc<eZdZdZdgZddejjdddddddf dede e e e fde d ed e e e e fd ee efd ed ede eeeefde eeeefddffd Ze jddfdejde e e fde de ee efde ee efdejf dZedddddddddddejdf dede ede e e e fd e ed e e e e fd e ed e ed e ede eeeefde eeeefde ee efdede ee efdejjfdZxZS)DeiTImageProcessora Constructs a DeiT 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 `preprocess`. size (`dict[str, int]` *optional*, defaults to `{"height": 256, "width": 256}`): Size of the image after `resize`. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling` filter, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. Can be overridden by `do_center_crop` in `preprocess`. crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`): Desired output size when applying center-cropping. Can be overridden by `crop_size` in `preprocess`. 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_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. 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. pixel_valuesTNgp? do_resizesizeresampledo_center_crop crop_sizerescale_factor do_rescale do_normalize image_mean image_stdreturnc  Ntjdi| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_dS)N)heightwidthr$ param_name)super__init__rr r!r"r#r$r&r%r'r r(r r)) selfr r!r"r#r$r%r&r'r(r)kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/deit/image_processing_deit.pyr4zDeiTImageProcessor.__init__Ts ""6"""'ttc-J-JT""!*!6IIsUX**DZ&/&;AVimage data_formatinput_data_formatc t|}d|vsd|vr$td||d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. r-r.zFThe `size` dictionary must contain the keys `height` and `width`. Got )r!r"r;r<)r ValueErrorkeysr )r5r:r!r"r;r<r6 output_sizes r8r zDeiTImageProcessor.resizetsFT"" 4  7$#6#6sfjfofofqfqsstt tH~tG}5   #/       r9imagesreturn_tensorsc  ||n|j}||n|j}||n|j}||n|j}||n|j}| | n|j} | | n|j} | | n|j} ||n|j}t|}||n|j }t|d}t|}t|stdt||| | | ||||| d|D}|r/t|drt dt%|dg}|D]}|r|||| }|r||| }|r||| }| r||| |  }|| fd |D}d|i}t1|| 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 `resize`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): PILImageResampling filter to use if resizing the image 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 image after center crop. If one edge the image is smaller than `crop_size`, it will be padded with zeros and then cropped 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. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - `None`: 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. 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$r0zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) r&r%r'r(r)r#r$r r!r"c,g|]}t|Sr2)r).0r:s r8 z1DeiTImageProcessor.preprocess..s <<.$s9    ({N_ ` ` `   r9r)data tensor_type)r r"r#r&r%r'r(r)r!rr$rrr>rrlogger warning_oncerr center_croprescale normalizeappendr)r5rAr r!r"r#r$r&r%r'r(r)rBr;r< all_imagesr:rLs `` r8 preprocesszDeiTImageProcessor.preprocesssB"+!6IIDN '388+9+E4K^#-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN 'ttTYT""!*!6IIDN !) DDD )&11F## :  &!)%!) =vay I I   % %E t %dXar ss k((u9Xi(jj m 5Zk ll jiSd'   e $ $ $ $     #    '>BBBBr9)__name__ __module__ __qualname____doc__model_input_namesPILImageBICUBICboolrdictstrintrrfloatlistr4npndarrayr r rFIRSTrrrU __classcell__)r7s@r8rr/s\B(()-'*y'8#.2,3!:>9=WWWtCH~&W% W  W DcN+ Wc5j)WWWU5$u+#567WE%e"456W WWWWWWH(:'A>BDH . . z. 38n. % . eC)9$9:; . $E#/?*?$@A .  . . . . `%$&&%))-)-.2%)*.'+:>9=;?(8(>DHECECECD>ECtCH~& EC ! ECDcN+ECTNEC!ECtnECU5$u+#567ECE%e"456EC!sJ!78EC&EC$E#/?*?$@AEC !ECECEC'&ECECECECECr9r)&rYtypingrrnumpyrdimage_processing_utilsrrrimage_transformsr r image_utilsr r r rrrrrrrrutilsrrrrutils.import_utilsrr[ get_loggerrVrNr__all__r2r9r8rqs&%""""""""UUUUUUUUUUCCCCCCCC                          _^^^^^^^^^^^******JJJ  H % % ;zCzCzCzCzC+zCzC zCz r9