T^(hRdZddlmZmZmZmZmZddlZddl m Z m Z m Z ddl mZmZmZmZddlmZmZmZmZmZmZmZmZmZmZmZmZmZddl m!Z!m"Z"m#Z#e#jHe%Z&e"rddl'Z'Gd d e Z(d gZ)y) z Image processor class for LLaVa.)DictListOptionalTupleUnionN)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_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availableloggingc$&eZdZdZdgZdddej ddddddddf deded ee e fd ed ed ee e fd ede e e fdede e e ee fde e e ee fdeddffd Z ddej"de e ee e e ffde e e efde e e efdej(f dZej ddfdej"d ee e fd ede e e efde e e efdej"f dZdddddddddddddej.dfdede ede ed e ee e fd e ed e ed e e d e ede e de ede e e ee fde e e ee fde ede e e efde ede e e efdej6j6f"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  Vt|d i| ||nddi}t|d}||nddd}t|dd}||_||_||_||_||_||_||_ ||_ | |_ | | nt|_ | | nt|_| |_gd |_y) N shortest_edgeF)default_to_square)heightwidthTr()r3 param_name)imagesr#r$r%r&r'r(r)r*r+r,r-r.return_tensors data_formatinput_data_format)super__init__r r#r$r%r&r'r(r)r*r+rr,rr-r._valid_processor_keys)selfr#r$r%r&r'r(r)r*r+r,r-r.kwargs __class__s n/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/llava/image_processing_llava.pyr=zLlavaImageProcessor.__init__bs "6"'tos-CTU;!*!6IsUX*DT&/&;,& "imagebackground_colorr9r:cnt||\}}|tjk(r|jdn|jd}||k(r|t |||}|S|}|St ||}t |tr|g}nt||k7rtd|d|tjk(r|tj|||f|j} t|D]\} } | | | ddddf<||kDr||z dz} || dd| | |zddf<n||z dz} || dddd| | |zf<n{tj|||f|j} t|D]\} } | | dddd| f<||kDr||z dz} || | | |zddddf<n||z dz} || dd| | |zddf<|t | ||}|S| }|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 mutli-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)rrFIRSTshapermax isinstanceintlen ValueErrornpzerosrH enumerate) r?rDrEr9r:r4r5 num_channelsmax_dimresulticolorstarts rB pad_to_squarez!LlavaImageProcessor.pad_to_squaresA>'u.?@ ):>N>T>T)Tu{{1~Z_ZeZefhZi U?*,E;@QR  L  Lfe$ & , 01  ! "l 2:<.Hqr   0 6 6 6XX|Wg>ekkRF%&67 (5"'q!Qw (v~ 6)a/7<q%%&.0!34 5Q.6;q!UUU]223XXw>ekkRF%&67 (5"'q!Qw (v~ 6)a/7<uuv~-q!34 5Q.6;q%%%-/23T_Sj ' =N O  qw  rCc 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. Tr1Fr4r5zASize must contain either 'shortest_edge' or 'height' and 'width'.)r%r3r:)r%r&r9r:)rPr r) r?rDr%r&r9r:r@r3 output_sizes rBrzLlavaImageProcessor.resizes2! d "(D %   'T/NDM2D`a a2 //    #/     rCr7r8c ||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|jt!|}t#|s t%dt'|| | | | ||||| | r|Dcgc] }t)|}}|Dcgc] }t+|}}t-|d r|rt.j1d |t3|d }g}|D]}|r.|j5|t7d |jD| }|r|j9|||| }|r|j;|||}|r|j=|| |}| r|j?|| | |}tA|||}|jC|tEd|i|Scc}wcc}w)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. r%F)r6r3r(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$r%r&rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.c38K|]}t|dzyw)N)rN).0xs rB z1LlavaImageProcessor.preprocess..s*QA3q3w<*Qs)rDrEr:)rDr%r&r:)rDr%r:)rDscaler:)rDmeanstdr:)input_channel_dimr")data tensor_type)#r#r$r%r r&r'r(r)r*r+r,r-r.rkeysr>rrrPrr rrlogger warning_oncerrZtupler center_croprescale normalizerappendr )r?r7r#r$r%r&r'r(r)r*r+r,r-r.r8r9r:r@rDprocessed_imagess rB preprocesszLlavaImageProcessor.preprocesssT"-4;;!*!6IDNN 'tTYYTfN'38+9+E4K^K^!*!6IDNN !) W[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^ DLfLfg$V,F#:  &!)%!)  9?@nU+@F@6<vay I  +E**%**Q*Q%Q&7+  %dXar s((u9Xi(j 5Zk ljiSd'0{VghE  # #E */ +2.2B!CQ_``SA=s >I I%)rNN)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrstrrNrfloatrrr=rQndarrayrrarrayrZrrJrrPILImagert __classcell__)rAs@rBr!r!5s(T((#'9'A'A#$(,3!:>9=#3 3 3 38n 3 % 3  3 S>3 3 c5j)3 3 U5$u+#5673 E%e"4563 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"&$()-15)-#'%)*.'+:>9=)-;?2B2H2HDH#ZaZaZaD> Za tCH~& Za -. Za!ZaC=ZaTNZa!ZatnZaU5$u+#567ZaE%e"456Za!Za!sJ!78Za ./!Za"$E#/?*?$@A#Za& 'ZarCr!)*rxtypingrrrrrnumpyrQimage_processing_utilsr r r image_transformsr r rr image_utilsrrrrrrrrrrrrrutilsrrr get_loggerrurlrr!__all__r;rCrBrsz'55UU >=   H %|a,|a~ ! !rC