qif ddlmZddlZddlmZmZmZddlm Z m Z m Z ddl m Z mZmZmZmZmZmZmZmZmZmZmZddlmZddlmZmZmZmZerddl Z ejBe"Z#Gd d ed Z$Gd deZ%dgZ&y))IterableN)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_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) ImagesKwargs) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingceZdZUdZeed<y)JanusImageProcessorKwargsz 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. min_sizeN)__name__ __module__ __qualname____doc__int__annotations__b/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/janus/image_processing_janus.pyrr4s Mr&rF)totalc"eZdZdZdgZeZdddejdddddddf de de e e fdzd e d ed e d e e zd e de ee zdzde ee zdzde dzde dzddffd Zejddfdej"de e e fe zd ede ezdzde ezdzdej"f dZeddddddddddddej*dfdede dzde e e fdzd edzd e dzd e dzd e dzde ee zdzde ee zdzde ezdzde dzde ee e e fzdzde dzdede ezdzdej4j4f dZ ddej"de ee e e fzde ezdzde ezdzdej"f dZ d ded e dzd e dzd e dzdee dzdee dzde dzde dzfdZ d!dej"de ee zde ee zde ezdzdej"f dZxZ 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. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to square or not. pixel_valuesTNgp? do_resizesizerresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbdo_padreturnc  Lt |di| ||nddd}t|d}||_||_||_||_||_||_||nt|_ | | nt|_ | |_ | |_||_|d|_yt#d|D|_y)Ni)heightwidthTdefault_to_square)r=r=c38K|]}t|dzyw)N)r#).0xs r' z/JanusImageProcessor.__init__..s)K1#a#g,)Ksr%)super__init__rr-r.r/r0r1r2r r3r r4r5r6rbackground_colortuple)selfr-r.rr/r0r1r2r3r4r5r6kwargs __class__s r'rDzJanusImageProcessor.__init__js "6"'tc-JTT:"   $,((2(>*DT&/&;,    $3D !$))K )K$KD !r&image data_formatinput_data_formatc r| t|}t||\}}t||} t|d}|d|dk7rt d|dd|d|d}|| z } tt || z|j tt || z|j g} t|f| |||d|}|S)an 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"`. 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. Tr;r9r:z5Output height and width must be the same. Got height=z and width=)r.r/rKrL)rrmaxr ValueErrorroundrr ) rGrJr.r/rKrLrHr9r:max_sizedeltaoutput_size_nonpaddeds r'r zJanusImageProcessor.resizesF  $ >u E &u.?@ vu%TT: >T'] *GXGWWbcghocpbqr H~x fun%t}} 5 eem$dmm 4!    &#/     r&imagesreturn_tensorsrEc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} | | n |j} | | n |j} ||n |j}t|d}|j|}t|}t|s tdt!||||| |||| r|Dcgc] }t#|}}|Dcgc] }t%|}}|r#t'|drt(j+d|t-|d}|r"|Dcgc]}|j/||||}}| r!|Dcgc]}|j1|| |}}|r!|Dcgc]}|j3||| }}|r"|Dcgc]}|j5||| | }}|Dcgc]}t7||| }}t9d |i| }|Scc}wcc}wcc}wcc}wcc}wcc}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_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. background_color (`tuple[int, int, int]`): The background color to use for the padding. do_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image to square or not. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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. Fr;zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)r0r1r2r3r4r-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.)rJr.r/rL)rJrErL)rJscalerLrJmeanstdrLinput_channel_dimr+data tensor_type)r-r/r0r1r2r3r4r5r6rEr.r fetch_imagesrrrOrrrrlogger warning_oncerr pad_to_squarerescale normalizer r)rGrTr-r.r/r0r1r2r3r4rUr5rEr6rKrLrJencoded_outputss r' preprocesszJanusImageProcessor.preprocesssH"+!6IDNN '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^!-4;;/?/K+QUQfQf'tTYYTU;""6*)&1F#rs s%!)%!  9?@nU+@F@6<vay I  $ %dXYj kF $   ""%5&7#F $ 5Rc dF $U^opF ou ej '{N_ `  '^V,DR`aeA=   s* H$!H)0H.H37H8H=<IcNt||\}}|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 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. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rr FIRSTshaper rN isinstancer#lenrOnpzerosrj enumerate) rGrJrErKrLr9r: num_channelsmax_dimresulticolorstarts r'rcz!JanusImageProcessor.pad_to_squarefs+<'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 r&c ||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)rJr3r4rL)rWrLr?zPIL.Image.Imager[r+r])r0r1r2r3r4rrnPILImagerorr unnormalizerdclipastyperpuint8r r LAST fromarrayappendr) rGrTr0r1r2r3r4rLrUr+rJr^s r' postprocesszJanusImageProcessor.postprocesss$.#9Zt 6D6Lt222R`'3'?|TEVEV #-#9Zt !*!6IDNN )&1 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>BBr&cd}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 ywNr%)r@rYrZs r'rBz2JanusImageProcessor.unnormalize.. sWytSus{Wsc3&K|] }d|z  yw)rzNr%)r@rZs r'rBz2JanusImageProcessor.unnormalize.. s;#a#g;srX)rnrrorOrFzipre)rGrJr3r4rLrsrev_image_mean rev_image_stds r'r}zJanusImageProcessor.unnormalizes0 j( +:,. ?<.@dehisetdu!vww$ 4J i *9~- >,?cdghqdrcs!tuu" l2IWC Is]%N((,L&*'9'A'A&-!1504&*""L"L38nt#"L "L % "L  "Le "L"LDK'$."L4;&-"Lt "Lt "L "LP(:'A'A59;? ?zz?38ns"?% ? ++d2 ? !11D8 ? ?B%&"&&*.2"&'+$(150426&*>B"(8(>(>;?!TT$;T38nt# T %t+ T 4K T TTkTDK'$.T4;&-Tj(4/Tt Tc3m 44t;Tt T&T !11D8!T" #T'Tr8959;? HzzHc3m 44H++d2 H !11D8 H  HZ#''+$()-(,(,%)1C1C4K1C 1C Tk 1C K$& 1C;%1C:1Cd 1Cp<@ +zz+HUO++8E?* + !11D8 +  +r&r*)'collections.abcrnumpyrpimage_processing_utilsrrrimage_transformsrr r image_utilsr r r rrrrrrrrrprocessing_utilsrutilsrrrrr{ get_loggerrrarr*__all__r%r&r'rs*%UUSS    -^^   H % EP,Pf ! !r&