qi@dZddlZddlmZmZmZddlmZm Z m Z m Z ddl m Z mZmZmZmZmZmZmZmZmZmZmZddlmZmZmZddlmZej>e Z!erddl"Z"ed Gd d eZ#d gZ$y) zImage processor class for CLIP.N)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availablelogging)requires)vision)backendsc!zeZdZdZdgZddej ddddddddf dedee e fdzded ed ee e fdzd ed e e zd ede e e zdzde e e zdzdeddffd Z ej ddfdejdee e fdede ezdzde ezdzdejf dZddddddddddddej$dfdededzdee e fdzdedzd edzd e dzd edzd e dzd edzde e e zdzde e e zdzdedzde ezdzdedzde ezdzdej,j,f dZxZS)CLIPImageProcessora Constructs a CLIP 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 the `preprocess` method. size (`dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`): Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image to the specified `crop_size`. Can be overridden by `do_center_crop` in the `preprocess` method. crop_size (`dict[str, int]` *optional*, defaults to 224): Size of the output image after applying `center_crop`. Can be overridden by `crop_size` 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 `do_rescale` 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 `rescale_factor` in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `[0.48145466, 0.4578275, 0.40821073]`): 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 `[0.26862954, 0.26130258, 0.27577711]`): 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. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  t |d i| ||nddi}t|d}||nddd}t|dd}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_gd |_d | vr#| d r|d|dd|_t#|d yyy) N shortest_edgeF)default_to_square)heightwidthTr$)r/ param_name)imagesr r!r"r#r$r%r&r'r(r)r*return_tensors data_formatinput_data_formatuse_square_size)super__init__rr r!r"r#r$r%r&r'r r(r r)r*_valid_processor_keysdelattr)selfr r!r"r#r$r%r&r'r(r)r*kwargs __class__s `/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/clip/image_processing_clip.pyr:zCLIPImageProcessor.__init__\s "6"'tos-CTU;!*!6IsUX*DT&/&;,& "&  &62C+D#'#84CXYDI D+ , ,E &imager5r6c d}d|vr|d}d}nd|vrd|vr |d|df}n tdt||||}t|f||||d|S) aZ Resize an image. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. 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. Tr-Fr0r1zASize must contain either 'shortest_edge' or 'height' and 'width'.)r!r/r6)r!r"r5r6) ValueErrorrr ) r=rBr!r"r5r6r>r/ output_sizes r@r zCLIPImageProcessor.resizes2! d "(D %   'T/NDM2D`a a2 //    #/     rAr3r4c ||n |j}||n |j}t|dd}||n |j}||n |j}||n |j }t|dd}||n |j }||n |j}| | n |j} | | n |j} | | n |j} | | n |j} t|j|j|j|}t!|}t#|s t%dt'||| | | ||||| | r|Dcgc] }t)|}}|Dcgc] }t+|}}|r#t-|d rt.j1d |t3|d }g}|D]m}|r|j5|||| }|r|j7||| }|r|j9||| }| r|j;|| | |}|j=|o|Dcgc]}t?|||}}d|i}tA|| Scc}wcc}wcc}w)aP 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 resizing. Shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. 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_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 center crop. Only has an effect if `do_center_crop` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image. 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 for normalization. Only has an effect if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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. r!F)r2r/r$T)captured_kwargsvalid_processor_keyszSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor) r%r&r'r(r)r#r$r r!r"rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rBr!r"r6)rBr!r6)rBscaler6)rBmeanstdr6)input_channel_dimr)data tensor_type)!r r!rr"r#r$r%r&r'r(r)r*rkeysr; fetch_imagesrrrDrrrrlogger warning_oncerr center_croprescale normalizeappendr r)r=r3r r!r"r#r$r%r&r'r(r)r*r4r5r6r>rB all_imagesrMs r@ preprocesszCLIPImageProcessor.preprocesssH"+!6IDNN 'tTYYTfN'38+9+E4K^K^!*!6IDNN !) W[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^ DLfLfg""6*)&1F#rs s%!)%!)  9?@nU+@F@6<vay I   %E %dXar s((u9Xi(j 5Zk ljiSd'   e $ %$$  ({N_ `  '>BBMA=: s?III )__name__ __module__ __qualname____doc__model_input_namesrBICUBICbooldictstrintfloatlistr:npndarrayr r FIRSTrrPILImagerX __classcell__)r?s@r@rr2s$L((&*'9'A'A#+/&-!1504#8-8-38nt#8-% 8-  8- S>D( 8-8-e 8-8-DK'$.8-4;&-8-8- 8-|(:'A'A59;? / zz/ 38n/ % / ++d2 / !11D8 /  / h"&&*.2&* $"&'+$(1504&*26/?/E/E;?!MCMC$;MC38nt# MC %t+ MC t MC:MC4KMC MCTkMCDK'$.MC4;&-MCt MCj(4/MC&,MC !11D8!MC$ %MCrAr)%r\numpyreimage_processing_utilsrrrimage_transformsrrr r image_utilsr r r rrrrrrrrrutilsrrrutils.import_utilsr get_loggerrYrQrhr__all__r8rAr@rss&UU    >=*   H % ;aC+aC aCH rA