`i:6dZddlmZmZddlZddlmZmZm Z ddl m Z m Z ddl mZmZmZmZmZmZmZmZmZmZmZddlmZmZmZejeZGd d eZ d gZ!dS) zImage processor class for Pvt.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingceZdZdZdgZddejdddddfdedee e e fded ed e e e fd ed ee e ee fd ee e ee fddffd Zejddfdejde e e fdedee e efdee e efdejf dZedddddddddejdf dedeedee e e fdeed eed ee d eed ee e ee fd ee e ee fdee e efde e efdee e effdZxZS)PvtImageProcessora Constructs a PVT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `(size["height"], size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by the `resample` 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. 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_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_DEFAULT_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_DEFAULT_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_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stdreturnc  tjdi| ||nddd}t|}||_||_||_||_||_||_||nt|_ ||nt|_ dS)N)heightwidth) super__init__rrrr!rrr r r"r r#) selfrrrrr r!r"r#kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/pvt/image_processing_pvt.pyr+zPvtImageProcessor.__init__Ks ""6"""'ttc-J-JT"""$(   ,(2(>**DY&/&;AUimage data_formatinput_data_formatc t|}d|vsd|vr$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.BILINEAR`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`. 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 )rrr2r3)r ValueErrorkeysr )r,r1rrr2r3r- output_sizes r/r zPvtImageProcessor.resizedsFT"" 4  7$#6#6sfjfofofqfqsstt tH~tG}5   #/       r0imagesreturn_tensorsc  ||nj}||nj}||nj}njnjnj  nj ||nj}t|t|}t|stdt|| ||d|D}|r/t|drtd t!|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`): Dictionary in the format `{"height": h, "width": w}` specifying the size of the output image after resizing. resample (`PILImageResampling` filter, *optional*, defaults to `self.resample`): `PILImageResampling` filter to use if resizing the image e.g. `PILImageResampling.BILINEAR`. Only has an effect if `do_resize` is set to `True`. 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 to use if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use if `do_normalize` is set to `True`. 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. NzkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rr r!r"r#rrrc,g|]}t|Sr))r).0r1s r/ z0PvtImageProcessor.preprocess..s <<.s> %i(^o ppr0c@g|]}|S))r1scaler3)rescale)r<r1r3r r,s r/r=z0PvtImageProcessor.preprocess..s< 5Rc ddr0cBg|]}|S))r1meanstdr3) normalize)r<r1r"r#r3r,s r/r=z0PvtImageProcessor.preprocess..s>U^oppr0c4g|]}t|S))input_channel_dim)r )r<r1r2r3s r/r=z0PvtImageProcessor.preprocess.. s7   ej '{N_ ` ` `   r0r)data tensor_type)rrr!rr r"r#rrrrr5rrlogger warning_oncerr)r,r8rrrrr r!r"r#r9r2r3rIr?s` ` ` `` `` @r/ preprocesszPvtImageProcessor.preprocesssqx"+!6IIDN #-#9ZZt '3'?||TEV '388+9+E4K^#-#9ZZt !*!6IIDN 'ttTY!$'' )&11F## :  &!)%! =vay I I   #F  #F  #F      nt   '>BBBBr0)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrintrfloatlistr+npndarrayr r rFIRSTrrrM __classcell__)r.s@r/rr*s <(()-'9'B,3!:>9=VVVtCH~&V% V  V c5j) VVU5$u+#567VE%e"456V VVVVVV:(:'B>BDH . . z. 38n. % . eC)9$9:; . $E#/?*?$@A .  . . . . `%$&&%))-15%)*.'+:>9=;?4D4JDH|C|C|CD>|CtCH~& |C -. |C TN |C!|Ctn|CU5$u+#567|CE%e"456|C!sJ!78|C3 001|C$E#/?*?$@A|C|C|C'&|C|C|C|C|Cr0r)"rQtypingrrnumpyrZimage_processing_utilsrrrimage_transformsr r image_utilsr r r rrrrrrrrutilsrrr get_loggerrNrKr__all__r)r0r/rfsh%$""""""""UUUUUUUUUUCCCCCCCC                          JIIIIIIIII  H % %gCgCgCgCgC*gCgCgCT  r0