`iHdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZerddlZej e!Z"Gd d eZ#d gZ$dS) z'Image processor class for EfficientNet.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_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_availableloggingc#eZdZdZdgZddejjdddddddddf dede e e e fd e d ed e e e e fd ee efd ededede eeeefde eeeefdeddffd Ze jddfdejde e e fd e de ee efde ee efdejf dZ ddejdee efdede ee efde ee eff dZedddddddddddddejdfdede ede e e e fd e ed e e e e fde ed e ed e ede ede eeeefde eeeefde ede ee efdede ee efdejjf dZxZS) EfficientNetImageProcessoraN Constructs a EfficientNet 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": 346, "width": 346}`): Size of the image after `resize`. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling` filter, *optional*, defaults to 0): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_center_crop (`bool`, *optional*, defaults to `False`): 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": 289, "width": 289}`): 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. rescale_offset (`bool`, *optional*, defaults to `False`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. 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. include_top (`bool`, *optional*, defaults to `True`): Whether to rescale the image again. Should be set to True if the inputs are used for image classification. pixel_valuesTNFgp? do_resizesizeresampledo_center_crop crop_sizerescale_factorrescale_offset do_rescale do_normalize image_mean image_std include_topreturnc  jtjdi| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | |_ | | nt|_ | | nt|_| |_dS)NiZ)heightwidthi!r" param_name)super__init__rrrr r!r"r%r#r$r&r r'r r(r))selfrrr r!r"r#r$r%r&r'r(r)kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/efficientnet/image_processing_efficientnet.pyr2z#EfficientNetImageProcessor.__init__Ws ""6"""'ttc-J-JT""!*!6IIsUX**DZ&/&;AV&image data_formatinput_data_formatc t|}d|vsd|vr$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.NEAREST`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.NEAREST`. 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 )rr r9r:)r ValueErrorkeysr )r3r8rr r9r:r4 output_sizes r6r z!EfficientNetImageProcessor.resize{sFT"" 4  7$#6#6sfjfofofqfqsstt tH~tG}5   #/       r7scaleoffsetc 6t|f|||d|}|r|dz }|S)a Rescale an image by a scale factor. If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is 1/127.5, the image is rescaled between [-1, 1]. image = image * scale - 1 If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1]. image = image * scale Args: image (`np.ndarray`): Image to rescale. scale (`int` or `float`): Scale to apply to the image. offset (`bool`, *optional*): Whether to scale the image in both negative and positive directions. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. )r?r9r:r )r3r8r?r@r9r:r4rescaled_images r6r z"EfficientNetImageProcessor.rescalesJ>!  KK\  `f    0+a/Nr7imagesreturn_tensorsc  ||nj}nj||nj}||nj}nj  nj | | nj}  nj  nj | | nj } nj tnj tdt|}t|stdt!|| || d|D}|r/t#|drt$dt)|d|rfd |D}|rfd |D}|r fd |D}| r fd |D}| r fd |D}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 `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`. rescale_offset (`bool`, *optional*, defaults to `self.rescale_offset`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. 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. include_top (`bool`, *optional*, defaults to `self.include_top`): Rescales the image again for image classification if set to True. 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"r.zkInvalid 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 c,g|]}t|Sr0)r).0r8s r6 z9EfficientNetImageProcessor.preprocess..>s <<.Ks> %dXYj kkr7c@g|]}|S))r8rr:) center_crop)rIr8r"r:r3s r6rJz9EfficientNetImageProcessor.preprocess..Qs<gl  u9Pa bbr7cBg|]}|S))r8r?r@r:rC)rIr8r:r#r$r3s r6rJz9EfficientNetImageProcessor.preprocess..VsH ~n`qr7cBg|]}|S)r8meanstdr: normalize)rIr8r'r(r:r3s r6rJz9EfficientNetImageProcessor.preprocess..^s>U^oppr7cBg|]}|dS)rrPrS)rIr8r(r:r3s r6rJz9EfficientNetImageProcessor.preprocess..ds>U Ufggr7c4g|]}t|S))input_channel_dim)r )rIr8r9r:s r6rJz9EfficientNetImageProcessor.preprocess..is7   ej '{N_ ` ` `   r7r)data tensor_type)rr r!r%r#r$r&r'r(r)rrr"rrr<rrlogger warning_oncerr)r3rErrr r!r"r%r#r$r&r'r(r)rFr9r:rXs` `` ` `` `` `` r6 preprocessz%EfficientNetImageProcessor.preprocesssMN"+!6IIDN '388+9+E4K^#-#9ZZt +9+E4K^+9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN %0%vay I I   #F  pvF  $ F  #F  #F      nt   '>BBBBr7)TNN)__name__ __module__ __qualname____doc__model_input_namesPILImageNEARESTboolrdictstrintrrfloatlistr2npndarrayrr r rFIRSTrrr\ __classcell__)r5s@r6rr.s $$L(()-'*y'8$.2,3$!:>9= !'!'!'tCH~&!'% !'  !' DcN+ !'c5j)!'!'!'!'U5$u+#567!'E%e"456!'!' !'!'!'!'!'!'P(:'A>BDH . . z. 38n. % . eC)9$9:; . $E#/?*?$@A .  . . . . h>BDH &&z&S%Z & & eC)9$9:; & $E#/?*?$@A &&&&P%$&&%))-)-.2%)*.)-'+:>9=&*;?(8(>DH#ZCZCZCD>ZCtCH~& ZC ! ZCDcN+ZCTNZC!ZC!ZCtnZCU5$u+#567ZCE%e"456ZCd^ZC!sJ!78ZC &!ZC"$E#/?*?$@A#ZC$ %ZCZCZC'&ZCZCZCZCZCr7r)%r`typingrrnumpyrkimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrutilsrrrrrb get_loggerr]rZr__all__r0r7r6rws.-""""""""UUUUUUUUUULLLLLLLLLL                          _^^^^^^^^^^^JJJ  H % %@C@C@C@C@C!3@C@C@CF ( (r7