rhAdddlmZddlmZmZddlZddlmZm Z m Z ddl m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z m!Z!e rddl"Z"e!jFe$Z%Gd d eZ&d gZ'y) )Iterable)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesmake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingceZdZdZdgZdddej ddddddf dedee e e fd e d ed ed e e e fd edee e ee fdee e ee fdeeddffd Zdej ddfdej"de e e e fe fdeee e e fd edee e efdee e efdej"fdZeddddddddddej,df dedeedee e e fd ed eed ee d eedee e ee fdee e ee fdee e efdeededee e efdej4j4fdZ ddej"de e ee e e ffdee e efdee e efdej8f dZ dded eed ee d eedeee deee dee dee fdZ d dej8de e ee fde e ee fdee e efdej8f dZ xZ!S)!JanusImageProcessora Constructs a JANUS 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 the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `{"height": 384, "width": 384}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. min_size (`int`, *optional*, defaults to 14): The minimum allowed size for the resized image. Ensures that neither the height nor width falls below this value after resizing. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` parameter 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 the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): 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. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): 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_resizesizemin_sizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc nt |di| ||nddd}t|d}||_||_||_||_||_||_||nt|_ | | nt|_ | |_ ||_|d|_yt!|D cgc]} t#| dzc} |_ycc} w)Ni)heightwidthTdefault_to_square)r2r2)super__init__r r"r#r%r&r'r(r r)rr*r+r$background_colortupleint)selfr"r#r$r%r&r'r(r)r*r+kwargsx __class__s /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/janus/image_processing_janus.pyr6zJanusImageProcessor.__init__cs "6"'tc-JTT:"   $,((2(>*DT&/&;,   $3D !$)*LA3q3w<*L$MD !*LsB2imager7 data_formatinput_data_formatc ||n |j}| t|}t||\}} t|| } t |d}|d|dk7rt d|dd|d|d}|| z } tt || z|jtt | | z|jg} t|f| |||d|}|j|||}|S) a Resize an image to dynamically calculated size. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]` or `int`): The size to resize the image to. If a dictionary, it should have the keys `"height"` and `"width"`. background_color (`tuple[int, int, int]`): The background color to use for the padding. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `None`: will be inferred from input input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. Tr0r.r/z5Output height and width must be the same. Got height=z and width=)r#r%r@rA)r?r7rA) r7rrmaxr ValueErrorr9r$r pad_to_square) r:r?r#r7r%r@rAr;r.r/max_sizedeltaoutput_size_nonpaddeds r>r zJanusImageProcessor.resizes-L0@/K+QUQfQf  $ >u E &u.?@ vu%TT: >T'] *GXGWWbcghocpbqr H~x FUN#T]] 3 EEM"DMM 2!    &#/    ""-/#   imagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} ||n |j}t|d}t|}t|s tdt||||| |||| r|Dcgc] }t|}}|Dcgc] }t|}}|r#t!|drt"j%d| t'|d} |r"|Dcgc]}|j)|||| }}|r!|Dcgc]}|j+||| }}|r"|Dcgc]}|j-||| | }}|Dcgc]}t/|| | }}t1d |i| }|Scc}wcc}wcc}wcc}wcc}wcc}w) am 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`): Controls the size of the image after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image values between [0 - 1]. 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 normalize the image by if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to normalize the image by 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. Fr0zkInvalid 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%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.)r?r#r%rA)r?scalerAr?meanstdrAinput_channel_dimr data tensor_type)r"r%r&r'r(r)r*r+r#r rrrDrr rrlogger warning_oncerr rescale normalizer r)r:rJr"r#r%r&r'r(r)r*rKr+r@rAr?encoded_outputss r> preprocesszJanusImageProcessor.preprocesss^@"+!6IDNN '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^'tTYYTU;)&1F#:  &!)%!  9?@nU+@F@6<vay I  $ %dXYj kF $ 5Rc dF $U^opF ou ej '{N_ `  '^V,DR`aOA=    s$G0G?G#GG$(G)cNt||\}}|tjk(r|jdn|jd}||k(r|t |||}|S|}|St ||}t |tr|g}nt||k7rtd|d|tjk(r~tj|||f|j} t|D]\} } | | | ddddf<||kDr||z dz} || dd| | |zddf<| S||z dz} || dddd| | |zf<| Stj|||f|j} t|D]\} } | | dddd| f<||kDr||z dz} || | | |zddddf<| S||z dz} || dd| | |zddf<| S)a} Pads an image to a square based on the longest edge. Args: image (`np.ndarray`): The image to pad. background_color (`int` or `tuple[int, int, int]`, *optional*, defaults to 0): The color to use for the padding. Can be an integer for single channel or a tuple of integers representing for multi-channel images. If passed as integer in mutli-channel mode, it will default to `0` in subsequent channels. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rrFIRSTshaper rC isinstancer9lenrDnpzerosr^ enumerate) r:r?r7r@rAr.r/ num_channelsmax_dimresulticolorstarts r>rEz!JanusImageProcessor.pad_to_squareXs+<'u.?@ ):>N>T>T)Tu{{1~Z_ZeZefhZi U?*,E;@QR  L  Lfe$ & , 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]223 XXw>ekkRF%&67 (5"'q!Qw (v~ 6)a/7<uuv~-q!34  !5Q.6;q%%%-/23 rIc ||n |j}|d|jz n|}||n |j}||n |j}||n |j}t |}t |dtjjrt|dkDr|S|dS|t|d}g} |D]} t| } |r|j| |||} |rC|j| ||} | jddjt j"} |rB|r@|dk(r;t%| t&j(| } tjj+| } | j-| d | i} |dk7r|nd}t/| | S) znApplies post-processing to the decoded image tokens by reversing transformations applied during preprocessing.Ng?r)r?r)r*rA)rMrAr3zPIL.Image.ImagerQr rS)r&r'r(r)r*rrbPILImagercrr unnormalizerXclipastyperduint8r rLAST fromarrayappendr) r:rJr&r'r(r)r*rArKr r?rTs r> postprocesszJanusImageProcessor.postprocesss$.#9Zt 6D6Lt222R`'3'?|TEVEV #-#9Zt !*!6IDNN $V, fQi 1 [1_6 ;&) ;  $ >vay I   'E"5)E((J)_p) U.Te f 1c*11"((; ~AR/R3E;K;P;Pduv ++E2    &! '$ -+9=N+NTX>BBrIcd}t|tr(t||k7r td|dt||g|z}t|tr(t||k7r td|dt||g|z}t dt ||D}t d|D}|j ||||}|S)a~ Unnormalizes `image` using the mean and standard deviation specified by `mean` and `std`. image = (image * image_std) + image_mean Args: image (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)` or `(num_channels, image_size, image_size)`): Batch of pixel values to postprocess. image_mean (`float` or `Iterable[float]`): The mean to use for unnormalization. image_std (`float` or `Iterable[float]`): The standard deviation to use for unnormalization. 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. rzmean must have z$ elements if it is an iterable, got zstd must have c3.K|] \}}| |z ywNr4).0rOrPs r> z2JanusImageProcessor.unnormalize..sWytSus{Wsc3&K|] }d|z  yw)rnNr4)r|rPs r>r}z2JanusImageProcessor.unnormalize..s;#a#g;srN)rbrrcrDr8ziprY)r:r?r)r*rArgrev_image_mean rev_image_stds r>rqzJanusImageProcessor.unnormalizes0 j( +:,. ?<.@dehisetdu!vww$ 4J i *9~- >,?cdghqdrcs!tuu" l2IWC Irr;s#J(()-'9'A'A,3!:>9=)- N NtCH~& N N % N  Nc5j) N NU5$u+#567 NE%e"456 N! N  NL<@'9'A'A>BDHIzzIDcNC'(I#5c3#78 I % I eC)9$9:; I$E#/?*?$@AI IV%&%))-'+%)*.'+:>9=;?)-(8(>(>DHEED>EtCH~& E % E TN E!EtnEU5$u+#567EE%e"456E!sJ!78E!E&E$E#/?*?$@AE E'ET>?>BDH HzzH U3S=%9 9:HeC)9$9:; H $E#/?*?$@A H  HZ&**.'+,0+/+/(,1C1CTN1C! 1C tn 1C T%[) 1CDK(1C$C=1C! 1CpEI +xx+%%01+/0 + $E#/?*?$@A +  +rIr)(collections.abcrtypingrrnumpyrdimage_processing_utilsrrr image_transformsr r r image_utilsr rrrrrrrrrrrrutilsrrrrro get_loggerrrVr__all__r4rIr>rss,%"UUSS   H %E,EP ! !rI