`iB(dZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd l m!Z!ej"e#Z$erddl%Z%e!d Gd d eZ&d gZ'dS)zImage processor class for CLIP.)OptionalUnionN)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"6eZdZdZdgZddejddddddddf dedee e e fded ed ee e e fd ed e e e fd edee e ee fdee e ee fdeddffd Zejddfdejde e e fdedee e efdee e efdejf dZddddddddddddejdfdedeedee e e fdeed eed ee d eed ee d eedee e ee fdee e ee fdeedee e efdeedee e efdejjf 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  tjd i| ||nddi}t|d}||nddd}t|dd}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_gd |_d | vr0| d r*|d|dd|_t#|d dSdSdS) N shortest_edgeF)default_to_square)heightwidthTr&)r1 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$r%r&r'r(r)r r*rr+r,_valid_processor_keysdelattr)selfr"r#r$r%r&r'r(r)r*r+r,kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/clip/image_processing_clip.pyr<zCLIPImageProcessor.__init___sC ""6"""'ttos-CTU;;;!*!6IIsUX**DT&/&;,& & & "&  & &62C+D &#'#84CXYYDI D+ , , , , , ' & & &imager7r8c d}d|vr |d}d}n(d|vrd|vr|d|df}ntdt||||}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/Fr2r3zASize must contain either 'shortest_edge' or 'height' and 'width'.)r#r1r8)r#r$r7r8) ValueErrorr r ) r?rDr#r$r7r8r@r1 output_sizes rBr zCLIPImageProcessor.resizes2! d " "(D %     'T//NDM2DD`aa a2 //      #/       rCr5r6c ^||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||}t!|}t#|st%dt'||| | | ||||| | r d |D}d |D}|r/t)|d rt*d t/|d g}|D]}|r||||}|r|||}|r|||}| r||| | }||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`): 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.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. Nr#F)r4r1r&T)captured_kwargsvalid_processor_keyszkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) r'r(r)r*r+r%r&r"r#r$c,g|]}t|Sr:)r .0rDs rB z1CLIPImageProcessor.preprocess..6s @@@nU++@@@rCc,g|]}t|Sr:)rrLs rBrNz1CLIPImageProcessor.preprocess..9s <<.Vs9    ({N_ ` ` `   rCr!)data tensor_type)r"r#rr$r%r&r'r(r)r*r+r,rkeysr= fetch_imagesrrrFrrlogger warning_oncerr center_croprescale normalizeappendr)r?r5r"r#r$r%r&r'r(r)r*r+r,r6r7r8r@ all_imagesrDrUs `` rB preprocesszCLIPImageProcessor.preprocesssL"+!6IIDN 'ttTYTfNNN'388+9+E4K^!*!6IIDN !) W[\\\ #-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN +9+E4K^ DLfgggg""6**)&11F## :  &!)%!)   A@@@@@F=vay I I   % %E t %dXar ss k((u9Xi(jj m 5Zk ll jiSd'   e $ $ $ $     #    '>BBBBrC)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrintrfloatlistr<npndarrayrr FIRSTrrPILImager` __classcell__)rAs@rBr r 5sa$$L(()-'9'A#.2,3!:>9=#8-8-8-tCH~&8-% 8-  8- DcN+ 8-8-c5j)8-8-U5$u+#5678-E%e"4568-8- 8-8-8-8-8-8-|(:'A>BDH / / z/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / / / / h%))-15)-#'%)*.'+:>9=)-;?2B2HDH!RCRCRCD>RCtCH~& RC -. RC ! RCC=RCTNRC!RCtnRCU5$u+#567RCE%e"456RC!RC!sJ!78RC./RC $E#/?*?$@A!RC$ %RCRCRCRCRCRCRCRCrCr )(rdtypingrrnumpyrmimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrrutilsrrrutils.import_utilsr get_loggerrarYrpr __all__r:rCrBr|s&%""""""""UUUUUUUUUU                            >=========******  H % %JJJ ;fCfCfCfCfC+fCfC fCR rC