`i:(dZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd lmZerddlZej e!Z"d Z#d Z$ed GddeZ%dgZ&dS)z#Image processor class for ImageGPT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requiresc|j}tjtj|d}tjtj|d}tj||}|dddfd|zz |dddfz}|S)Naxisr)Tnpsumsquarematmul)aba2b2abds /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/imagegpt/image_processing_imagegpt.pysquared_euclidean_distancer+-s A  ! 1 % % %B  ! 1 % % %B 1aB 111d7 a"fr$'{*A Hcz|dd}t||}tj|dS)Nrrr)reshaper+r argmin)xclustersr)s r*color_quantizer36s9 "aA"1h//A 9QQ   r,)vision)backendsceZdZdZdgZdddejddfdeee e e e j fde deeee fded e d e d dffd Zejddfd e j deee fdedeeeefdeeeefd e j f dZ dd e j deeeefdeeeefd e j fdZedddddddejdf dedee deeee fdeed ee d ee deee e e e j fdeeeefdeeeefdeeeefd ejjfdZfdZxZS)ImageGPTImageProcessora Constructs a ImageGPT image processor. This image processor can be used to resize images to a smaller resolution (such as 32x32 or 64x64), normalize them and finally color quantize them to obtain sequences of "pixel values" (color clusters). Args: clusters (`np.ndarray` or `list[list[int]]`, *optional*): The color clusters to use, of shape `(n_clusters, 3)` when color quantizing. Can be overridden by `clusters` in `preprocess`. do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's dimensions to `(size["height"], size["width"])`. Can be overridden by `do_resize` in `preprocess`. size (`dict[str, int]` *optional*, defaults to `{"height": 256, "width": 256}`): Size of the image after resizing. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image pixel value to between [-1, 1]. Can be overridden by `do_normalize` in `preprocess`. do_color_quantize (`bool`, *optional*, defaults to `True`): Whether to color quantize the image. Can be overridden by `do_color_quantize` in `preprocess`. pixel_valuesNTr2 do_resizesizeresample do_normalizedo_color_quantizereturnc tjdi|||nddd}t|}|tj|nd|_||_||_||_||_ ||_ dS)N)heightwidth) super__init__rr arrayr2r9r:r;r<r=) selfr2r9r:r;r<r=kwargs __class__s r*rEzImageGPTImageProcessor.__init__Ws ""6"""'ttc-J-JT"".6.B*** "   (!2r,image data_formatinput_data_formatc t|}d|vsd|vr$td||d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. rArBzFThe `size` dictionary must contain the keys `height` and `width`. Got )r:r;rKrL)r ValueErrorkeysr )rGrJr:r;rKrLrH output_sizes r*r zImageGPTImageProcessor.resizemsFT"" 4  7$#6#6sfjfofofqfqsstt tH~tG}5   #/       r,c6t|d||}|dz }|S)a Normalizes an images' pixel values to between [-1, 1]. Args: image (`np.ndarray`): Image to normalize. 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. g?)rJscalerKrLr)r )rGrJrKrLs r* normalizez ImageGPTImageProcessor.normalizes)"e9+arsss  r,imagesreturn_tensorsc  ||nj}njtnj||nj}||nj}||nj}tj|}t|}t|stdt||r|tdd|D}|r/t|drtd t!|d |r fd|D}|r fd |D}|r fd |D}tj|}t#|||jdd }|jd} || d }t)|}d |i} n fd |D}d|i} t+| |S)aX 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_normalize=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. 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_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image do_color_quantize (`bool`, *optional*, defaults to `self.do_color_quantize`): Whether to color quantize the image. clusters (`np.ndarray` or `list[list[int]]`, *optional*, defaults to `self.clusters`): Clusters used to quantize the image of shape `(n_clusters, 3)`. Only has an effect if `do_color_quantize` 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. Only has an effect if `do_color_quantize` is set to `False`. 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.)r9r:r;z8Clusters must be specified if do_color_quantize is True.c,g|]}t|SrC)r).0rJs r* z5ImageGPTImageProcessor.preprocess..s <<.s> %dXYj kkr,c>g|]}|S))rJrL)rS)rXrJrLrGs r*rYz5ImageGPTImageProcessor.preprocess..s+kkk[`dnn5DUnVVkkkr,cFg|]}t|tjSrC)r r LAST)rXrJrLs r*rYz5ImageGPTImageProcessor.preprocess..s,wwwgl1%9I9NPabbwwwr,r. input_idsc2g|]}t|SrC)r )rXrJrKrLs r*rYz5ImageGPTImageProcessor.preprocess..(s(mmm]b1%FWXXmmmr,r8)data tensor_type)r9r:rr;r<r=r2r rFrrrNrrlogger warning_oncerr3r/shapelistr) rGrTr9r:r;r<r=r2rUrKrL batch_sizer`s ` `` `` r* preprocessz!ImageGPTImageProcessor.preprocesssl"+!6IIDN 'ttTYT""'388'3'?||TEV 1B1N--TXTj'3888H%%$V,,F## :  &     Y!1WXX X=vay I I   #F  lkkkkkdjkkkF  ,wwwwpvwwwFXf%%F#FH55==fl3B3>OPPF aJ^^J33F&\\F(DDmmmmmflmmmF"F+D>BBBBr,ct}|d=t|dtjr|d|d<gd}|D] }||vrd||< |S)Nr2) image_mean image_stdrescale_factor do_rescale)rDto_dictget isinstancer ndarraytolist)rGoutput missing_keyskeyrIs r*rmzImageGPTImageProcessor.to_dict,s"" ::j ! ! -*VJ=OQSQ[2\2\ -!' !3!:!:!3 3 tCH~& 3 % 33 3 3333334(:'B>BDH . . z. 38n. % . eC)9$9:; . $E#/?*?$@A .  . . . . f?CDH zeC)9$9:;$E#/?*?$@A   *%$&&%))-15'+,0AE;?>N>TDHwCwCwCD>wCtCH~& wC -. wC tn wC$D>wC5d3i"*!<=>wC!sJ!78wCeC)9$9:;wC$E#/?*?$@AwC wCwCwC'&wCr         r,r7)'rxtypingrrnumpyr image_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrutilsrrrrutils.import_utilsrr get_loggerrurbr+r3r7__all__rCr,r*rs*)""""""""UUUUUUUUUULLLLLLLLLL                      _^^^^^^^^^^^******JJJ  H % %       ;zzzzz/zz zz $ $r,