`i SdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z e j!e"Z#erddl$Z$Gd d eZ%d gZ&dS) z Image processor class for LLaVa.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availableloggingc$eZdZdZdgZdddejddddddddf deded ee e e fd ed ed ee e e fd ede e e fdedee e ee fdee e ee fdeddffd Z ddejde e ee e e ffdee e efdee e efdejf dZejddfdejd e e e fd edee e efdee e efdejf dZdddddddddddddejdfdedeedeed ee e e fd eed eed ee d eedee deedee e ee fdee e ee fdeedee e efdeedee e efdejjf"dZxZS) LlavaImageProcessora Constructs a LLaVa image processor. Args: do_pad (`bool`, *optional*, defaults to `False`): Whether to pad the image to a square based on the longest edge. The padding value is determined by the `image_mean` parameter. Can be overridden by `do_pad` in the `preprocess` method. 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_valuesFTNgp?do_pad 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 |_dS) N shortest_edgeF)default_to_square)heightwidthTr%)r0 param_name)imagesr r!r"r#r$r%r&r'r(r)r*r+return_tensors data_formatinput_data_format)super__init__rr r!r"r#r$r%r&r'r(r r)rr*r+_valid_processor_keys)selfr r!r"r#r$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/llava/image_processing_llava.pyr:zLlavaImageProcessor.__init__bs ""6"""'ttos-CTU;;;!*!6IIsUX**DT&/&;,& & & """rimagebackground_colorr6r7ct||\}}|tjkr |jdn |jd}||kr|t |||n|}|St ||}t |tr|g}n&t||krtd|d|tjkrytj |||f|j } t|D]\} } | | | ddddf<||kr||z dz} || dd| | |zddf<n||z dz} || dddd| | |zf<nxtj |||f|j } t|D]\} } | | dddd| f<||kr||z dz} || | | |zddddf<n||z dz} || dd| | |zddf<|t | ||n| }|S)a Pads an image to a square based on the longest edge. Args: image (`np.ndarray`): The image to pad. background_color (`int` or `tuple[int, int, int]`, *optional*, defaults to 0): The color to use for the padding. Can be an integer for single channel or a tuple of integers representing for multi-channel images. If passed as integer in multi-channel mode, it will default to `0` in subsequent channels. data_format (`str` or `ChannelDimension`, *optional*): 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. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for 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. If unset, will use the inferred format of the input image. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rrFIRSTshaper max isinstanceintlen ValueErrornpzerosrE enumerate) r<rArBr6r7r1r2 num_channelsmax_dimresulticolorstarts r? pad_to_squarez!LlavaImageProcessor.pad_to_squares>'u.?@@ ):>N>T)T)Tu{1~~Z_ZefhZi U??*,E;@QRRR  Lfe$$ & , ,  01   ! " "l 2 2r<rrr   0 6 6 6X|Wg>ekRRRF%&677 ( (5"'q!!!QQQwv~~ 6)a/7<qqq%%&.0!!!344 5Q.6;qqq!!!UUU]2233Xw>ekRRRF%&677 ( (5"'qqq!!!Qwv~~ 6)a/7<uuv~-qqq!!!344 5Q.6;qqq%%%-/23T_Sj ' =N O O Opv  r@c 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.Fr1r2zASize must contain either 'shortest_edge' or 'height' and 'width'.)r"r0r7)r"r#r6r7)rMr r ) r<rAr"r#r6r7r=r0 output_sizes r?r zLlavaImageProcessor.resizes2! d " "(D %     'T//NDM2DD`aa a2 //      #/       r@r4r5c ||n|j}||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}t+|d r|rt,d |t1|d }g}|D]}|r4||t5d|j D|}|r|||||}|r||||}|r||| |}| r||| | |}t?|||}| |tCd|i|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_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image to a square based on the longest edge. The padding value is determined by the `image_mean` parameter. 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)r3r0r%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$r%r!r"r#c,g|]}t|Sr8)r .0rAs r? z2LlavaImageProcessor.preprocess..s @@@nU++@@@r@c,g|]}t|Sr8)rr^s r?r`z2LlavaImageProcessor.preprocess..s <<z1LlavaImageProcessor.preprocess..s,*Q*QA3q3w<<*Q*Q*Q*Q*Q*Qr@)rArBr7)rAr"r#r7)rAr"r7)rAscaler7)rAmeanstdr7)input_channel_dimr)data tensor_type)"r r!r"rr#r$r%r&r'r(r)r*r+rkeysr; fetch_imagesrrrMrrlogger warning_oncerrWtupler center_croprescale normalizer appendr)r<r4r r!r"r#r$r%r&r'r(r)r*r+r5r6r7r=processed_imagesrAs r? preprocesszLlavaImageProcessor.preprocesssIT"-4;!*!6IIDN 'ttTYTfNNN'388+9+E4K^!*!6IIDN !) W[\\\ #-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN +9+E4K^ DLfgggg""6**)&11F## :  &!)%!)   A@@@@@F=vay I I  + +E **%**Q*Q*Q*Q*Q%Q%Q&7+  t %dXar ss k((u9Xi(jj m 5Zk ll jiSd'0{VghhhE  # #E * * * *.2B!CQ_````r@)rNN)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrrKrfloatlistr:rNndarrayrprrWr rGrrPILImagerv __classcell__)r>s@r?rr5s((T(()-'9'A#.2,3!:>9=#3 3 3 3 tCH~& 3 % 3  3 DcN+3 3 c5j)3 3 U5$u+#5673 E%e"4563 3  3 3 3 3 3 3 p>?>BDH LLzL U3S=%9 9:LeC)9$9:; L $E#/?*?$@A L  LLLLf(:'A>BDH / / z/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / / / / h"&$()-15)-#'%)*.'+:>9=)-;?2B2HDH#[a[a[a[aD> [a tCH~& [a -. [a![aC=[aTN[a![atn[aU5$u+#567[aE%e"456[a![a!sJ!78[a ./![a"$E#/?*?$@A#[a& '[a[a[a[a[a[a[a[ar@r)'rztypingrrnumpyrNimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrrrutilsrrr get_loggerrwrnrr__all__r8r@r?rs'&""""""""UUUUUUUUUU >=========  H % %JJJ}a}a}a}a}a,}a}a}a@ ! !r@