T^(h8dZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZddlmZmZmZmZerddlZej@e!Z"d Z#d Z$Gd d e Z%d gZ&y) z#Image processor class for ImageGPT.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc$|j}tjtj|d}tjtj|d}tj||}|dddfd|zz |dddfz}|S)Naxisr)Tnpsumsquarematmul)aba2b2abds t/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/imagegpt/image_processing_imagegpt.pysquared_euclidean_distancer,,sr A  ! 1 %B  ! 1 %B 1aB 1d7 a"fr$'{*A Hcl|jdd}t||}tj|dS)Nrrr)reshaper,r!argmin)xclustersr*s r+color_quantizer45s/ "aA"1h/A 99QQ r-ceZdZdZdgZdddej ddfdeee e e e jfde deee fded e d e d dffd Zej ddfd e jdeee fdedeeeefdeeeefd e jf dZ dd e jdeeeefdeeeefd e jfdZedddddddej*df dedee deee fded ee d ee deee e e e jfdeeeefdeeeefdeeeefd ej2j2fdZxZS)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 overriden 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_valuesNTr3 do_resizesizeresample do_normalizedo_color_quantizereturnc t|di|||nddd}t|}|tj|nd|_||_||_||_||_ ||_ y)N)heightwidth) super__init__r r!arrayr3r8r9r:r;r<) selfr3r8r9r:r;r<kwargs __class__s r+rDzImageGPTImageProcessor.__init__Usl "6"'tc-JT".6.B* "   (!2r-image data_formatinput_data_formatc t|}d|vsd|vrtd|j|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@rAzFThe `size` dictionary must contain the keys `height` and `width`. Got )r9r:rJrK)r ValueErrorkeysr )rFrIr9r:rJrKrG output_sizes r+r zImageGPTImageProcessor.resizeksyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r-c.t|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?)rIscalerJrKr)r )rFrIrJrKs r+ normalizez ImageGPTImageProcessor.normalizes#"e9+ars  r-imagesreturn_tensorsc V||n |j}||n |j}t|}||n |j}||n |j}||n |j }||n |j }tj|}t|}t|s tdt||||r | td|D cgc] } t| }} |r#t|drtj!d| t#|d} |r"|D cgc]} |j%| ||| }} |r |D cgc]} |j'| | }} |r|D cgc]} t)| t*j,| }} tj|}t/||j1|j2dd }|j2d} |j1| d }t5|}n|D cgc]} t)| | | }} d |i} t7| | Scc} wcc} wcc} wcc} wcc} w) 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.)r8r9r:z8Clusters must be specified if do_color_quantize is True.rzIt looks like you are trying to rescale already rescaled images. If you wish to do this, make sure to set `do_normalize` to `False` and that pixel values are between [-1, 1].)rIr9r:rK)rIrKr/)input_channel_dim input_ids)data tensor_type)r8r9r r:r;r<r3r!rErrrMrrrlogger warning_oncerr rRr rLASTr4r0shapelistr )rFrSr8r9r:r;r<r3rTrJrKrI batch_sizerXs r+ preprocessz!ImageGPTImageProcessor.preprocesss`l"+!6IDNN 'tTYYT"'38'3'?|TEVEV 1B1N-TXTjTj'3888H%$V,F#:  & !1WX X6<vay I  $ %dXYj kF djk[`dnn5DUnVkFk pvwgl1%9I9N9NPabwFwXXf%F#FH5==fll3B>OPF aJ^^J3F&\F$,E;RcdF V$>BBQ= lxsHH6H"H!*H&)NN)__name__ __module__ __qualname____doc__model_input_namesrBILINEARrrrintr!ndarrayboolrstrrDrr rRrFIRSTrrPILImager` __classcell__)rHs@r+r6r6;s.(( BF#'9'B'B!"&35d3i"**!<=>3 3 38n 3 % 33 3 34(:'B'B>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . f?CDH zzeC)9$9:;$E#/?*?$@A   *%&%)#'+'+,0AE;?>N>T>TDHzCzCD>zC38n zC % zC tn zC$D>zC5d3i"**!<=>zC!sJ!78zCeC)9$9:;zC$E#/?*?$@AzC zC'zCr-r6)'rdtypingrrrrnumpyr!image_processing_utilsrr r image_transformsr r r image_utilsrrrrrrrrrutilsrrrrrl get_loggerrarZr,r4r6__all__rBr-r+rws|*..UULL   _^   H %  pC/pCf $ $r-