cCi SSrSSKJrJr SSKrSSKJrJrJ r SSK J r J r J r Jr SSKJrJrJrJrJrJrJrJrJrJrJrJrJr SSKJrJrJ r \ RB"\"5r#\"5(aSSK$r$"S S \5r%S /r&g) 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$L^\rSrSrSrS/rSSS\RSSSSSSSS4 S\S \S \ \ \ \ 4S \S \S \ \ \ \ 4S\S\ \ \4S\S\ \ \\\4S\ \ \\\4S\SS4U4SjjjrS S\R$S\ \ \\ \ \ 44S\ \ \ \4S\ \ \ \4S\R$4 Sjjr\RSS4S\R$S \ \ \ 4S \S\ \ \ \4S\ \ \ \4S\R$4 SjjrSSSSSSSSSSSSS\R.S4S\S\ \S \ \S \ \ \ \ 4S \ \S \ \S \ \ S\ \S\ \S\ \S\ \ \\\4S\ \ \\\4S\ \S\ \ \ \4S\ \S\ \ \ \4S\R6R64"SjjrSrU=r$)!LlavaImageProcessor5a% 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  @>[TU]"S 0U D6 UbUOSS0n[USS9nUbUOSSS.n[USSS9nXlX lX0lX@lXPlX`lXpl Xl Xl U bU O[Ul U bU O[UlXl/S QUlg) N shortest_edgeF)default_to_square)heightwidthTr&)r1 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$r%r&r'r(r)r*r+r,kwargs __class__s j/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/llava/image_processing_llava.pyr;LlavaImageProcessor.__init__bs "6"'tos-CTU;!*!6IsUX*DT&/&;,& "imagebackground_colorr7r8cT[X5upVU[R:XaURSOURSnXV:XaUb[ XU5nU$UnU$[ XV5n[ U[5(aU/nO[U5U:wa[SUS35eU[R:Xas[R"XxU4URS9n [U5HupXU SS2SS24'M Xe:aX- S-n XSS2XU-2SS24'OX- S-n XSS2SS2XU-24'Or[R"XU4URS9n [U5HupXSS2SS2U 4'M Xe:aX- S-n XXU-2SS2SS24'OX- S-n XSS2XU-2SS24'Ub[ XU5nU$U nU$)a  Pads an image to a square based on the longest edge. Args: image (`np.ndarray`): The image to pad. background_color (`int` or `tuple[int, int, int]`, *optional*, defaults to 0): The color to use for the padding. Can be an integer for single channel or a tuple of integers representing for multi-channel images. If passed as integer in multi-channel mode, it will default to `0` in subsequent channels. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. If unset, will use the inferred format of the input image. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rrFIRSTshaper max isinstanceintlen ValueErrornpzerosrG enumerate) r=rCrDr7r8r2r3 num_channelsmax_dimresulticolorstarts r@ pad_to_square!LlavaImageProcessor.pad_to_squares>'u@ ):>N>T>T)Tu{{1~Z_ZeZefhZi ?*,E@QR  L  Lf$ & , , 01  ! "l 2:<.Hqr   0 6 6 6XX|g>ekkRF%&67"'q!Qw8~ )a/7ekkRF%&67"'q!Qw8~ )a/7r1 output_sizes r@r LlavaImageProcessor.resizes2! d "(D %   'T/NDM2D`a a2 //    #/     rBr5r6c 4UbUO URnUbUO URnUbUO URn[USSS9nUbUO URnUbUO UR nUbUO UR n[USSS9nUbUO URnU bU O URn U bU O URn U bU O URn U bU O URn U bU O URn [UR5URS9 UR!U5n[#U5n[%U5(d ['S5e[)UU U U U UUUUUS9 U (aUVs/sHn[+U5PM nnUVs/sHn[-U5PM nn[/US 5(aU(a[0R3S 5 Uc[5US 5n/nUHnU(a+UR7U[9S UR55US 9nU(aUR;UXEUS 9nU(aUR=UUUS9nU(aUR?UU US9nU (aURAUXUS9n[CUUUS9nUREU5 M [GSU0US9$s snfs snf)aG 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. r#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$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.c3># UHn[US-5v M g7f)N)rM).0xs r@ 1LlavaImageProcessor.preprocess..s*QA3q3w<<s)rCrDr8)rCr#r$r8)rCr#r8)rCscaler8)rCmeanstdr8)input_channel_dimr )data tensor_type)$r!r"r#rr$r%r&r'r(r)r*r+r,rkeysr< fetch_imagesrrrOrr rrlogger warning_oncerrYtupler center_croprescale normalizer appendr)r=r5r!r"r#r$r%r&r'r(r)r*r+r,r6r7r8r>rCprocessed_imagess r@ preprocessLlavaImageProcessor.preprocesssT"-4;;!*!6IDNN 'tTYYTfN'38+9+E4K^K^!*!6IDNN !) W[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^ DLfLfg""6*)&1F##:  &!)%!)  9?@nU+F@6<vay I E**%**Q*Q%Q&7+  %dar s((u9Xi(j 5Zk ljSd'0{VghE  # #E */2.2B!CQ_``SA=s J4J) r<r&r%r,r)r!r'r"r*r+r$r(r#)rNN)__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBICUBICboolrdictstrrMrfloatlistr;rPndarrayrqrrYr rIrrPILImagerw__static_attributes__ __classcell__)r?s@r@rr5s(T(()-'9'A'A#.2,3!:>9=#3 3 3 tCH~& 3 % 3  3 DcN+3 3 c5j)3 3 U5$u+#5673 E%e"4563 3  3 3 p>?>BDH LzzL U3S=%9 9:LeC)9$9:; L $E#/?*?$@A L  Lf(:'A'A>BDH / zz/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / h"&$()-15)-#'%)*.'+:>9=)-;?2B2H2HDH#[a[a[aD> [a tCH~& [a -. [a![aC=[aTN[a![atn[aU5$u+#567[aE%e"456[a![a!sJ!78[a ./![a"$E#/?*?$@A#[a& '[a[arBr)'r}typingrrnumpyrPimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrrrutilsrrr get_loggerryrorr__all__r9rBr@rsx'"UU >=   H %}a,}a@ ! !rB