o i:@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd lmZerQddlZe e!Z"d d Z#d d Z$eddGdddeZ%dgZ&dS)z#Image processor class for ImageGPT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requirescCsf|j}tjt|dd}tjt|dd}t||}|dddfd||dddf}|S)Naxisr)Tnpsumsquarematmul)aba2b2abdr(j/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/imagegpt/image_processing_imagegpt.pysquared_euclidean_distance-s  (r*cCs$|dd}t||}tj|ddS)Nrrr)reshaper*rargmin)xclustersr'r(r(r)color_quantize6s  r0)vision)backendscseZdZdZdgZdddejddfdeee e e e j fde deeee fded e d e d dffd d Zejddfde j deee fdedeeeefdeeeefd e j f ddZ  dde j deeeefdeeeefd e j fddZedddddddejdf dedee deeee fdeed ee d ee deee e e e j fdeeeefdeeeefdeeeefd ejjfddZfddZZS)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_valuesNTr/ do_resizesizeresample do_normalizedo_color_quantizereturnc sjtjdi||dur|nddd}t|}|dur!t|nd|_||_||_||_||_ ||_ dS)N)heightwidthr() super__init__rrarrayr/r5r6r7r8r9)selfr/r5r6r7r8r9kwargs __class__r(r)r?Ws  zImageGPTImageProcessor.__init__image data_formatinput_data_formatcKsTt|}d|vs d|vrtd||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 )r6r7rFrG)r ValueErrorkeysr )rArEr6r7rFrGrB output_sizer(r(r)r ms#zImageGPTImageProcessor.resizecCst|d||d}|d}|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?)rEscalerFrGr)r)rArErFrGr(r(r) normalizesz ImageGPTImageProcessor.normalizeimagesreturn_tensorsc s|dur|nj}durnjtdurnj|dur%|nj}|dur.|nj}|dur7|nj}t|}t |}t |sKt dt |d|r\|dur\t ddd|D}|rpt |drptddurzt|d|rfd d|D}|rfd d|D}|rŇfd d|D}t|}t|||jdd }|jd} || d }t|}d |i} nfdd|D}d|i} t| |dS)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.)r5r6r7z8Clusters must be specified if do_color_quantize is True.cSsg|]}t|qSr()r.0rEr(r(r) sz5ImageGPTImageProcessor.preprocess..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].csg|] }j|dqS))rEr6r7rG)r rO)rGr7rAr6r(r)rQscsg|] }j|dqS))rErG)rLrO)rGrAr(r)rQcsg|] }t|tjqSr()r r LASTrO)rGr(r)rQrRr+ input_idscsg|]}t|qSr()r rO)rFrGr(r)rQ(sr4)data tensor_type)r5r6rr7r8r9r/rr@rrrHrrlogger warning_oncerr0r,shapelistr) rArMr5r6r7r8r9r/rNrFrG batch_sizerUr()rFrGr7rAr6r) preprocesssX6        z!ImageGPTImageProcessor.preprocesscs^t}|ddurt|dtjr|d|d<gd}|D] }||vr,d||<q"|S)Nr/) image_mean image_stdrescale_factor do_rescale)r>to_dictget isinstancerndarraytolist)rAoutput missing_keyskeyrCr(r)ra,s zImageGPTImageProcessor.to_dict)NN)__name__ __module__ __qualname____doc__model_input_namesr BILINEARrrrZintrrdbooldictstrr?r r rLrFIRSTr rPILImager\ra __classcell__r(r(rCr)r3<s   3     yr3)'rltypingrrnumpyrimage_processing_utilsrrrimage_transformsrr r image_utilsr r r rrrrrrutilsrrrrutils.import_utilsrrt get_loggerrirWr*r0r3__all__r(r(r(r)s",    ~