`iwfddlmZddlmZmZddlZddlmZm Z m Z ddl m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZm Z erddl!Z!e j"e#Z$Gd d eZ%d gZ&dS) )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_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc#6eZdZdZdgZdddejdddddddf dedee e e fd e d ed ed e e e fd edee e ee fdee e ee fdeedeeddffd Zejddfdejde e e e fe fd edee e efdee e efdejf dZeddddddddddddejdfdedeedee e e fd eed eed ee d eedee e ee fdee e ee fdee e efdeedee e ee e e ffdeededee e efdejjf dZ d dejde e ee e e ffdee e efdee e efdejf dZ d!ded eed ee d eedeee deee dee dee fdZ d"dejde e ee fde e ee fdee e efdejf 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_resizesizemin_sizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbdo_padreturnc  ~tjdi| ||nddd}t|d}||_||_||_||_||_||_||nt|_ | | nt|_ | |_ | |_||_| d|_dSt#d|D|_dS)Ni)heightwidthTdefault_to_square)r2r2c3:K|]}t|dzVdS)N)int).0xs /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/janus/image_processing_janus.py z/JanusImageProcessor.__init__..s,)K)K1#a#g,,)K)K)K)K)K)K)super__init__r r!r"r$r%r&r'r r(rr)r*r+r#background_colortuple)selfr!r"r#r$r%r&r'r(r)r*r+kwargs __class__s r8r=zJanusImageProcessor.__init___s ""6"""'ttc-J-JTT:::"   $,((2(>**DT&/&;,    $3D ! ! !$))K)K )K)K)K$K$KD ! ! !r:image data_formatinput_data_formatc |t|}t||\}}t||} t|d}|d|dkr!t d|dd|d|d}|| z } tt || z|jtt || z|jg} 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. NTr0r.r/z5Output height and width must be the same. Got height=z and width=)r"r$rDrE)rrmaxr ValueErrorr5r#r ) r@rCr"r$rDrErAr.r/max_sizedeltaoutput_size_nonpaddeds r8r zJanusImageProcessor.resizes F  $ >u E E &u.?@@ vu%%TT::: >T'] * *rXrrcghocprr H~x FUN##T] 3 3 EEM""DM 2 2!    &#/       r:imagesreturn_tensorsr>c z ||nj}nj||nj}nj||nj}nj  nj | | nj} | | nj}  nj nj td |}t|}t|stdt!|| || r d|D}d|D}|r/t#|drt$d t)|d|rfd |D}| r fd |D}|rfd |D}|r fd |D}fd|D}t+d|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_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.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. NFr0zkInvalid 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$c,g|]}t|Sr;)r r6rCs r8 z2JanusImageProcessor.preprocess..,s @@@nU++@@@r:c,g|]}t|Sr;)rrPs r8rQz2JanusImageProcessor.preprocess../s <<.<s> %dXYj kkr:c@g|]}|S))rCr>rE) pad_to_square)r6rCr>rEr@s r8rQz2JanusImageProcessor.preprocess..CsI  ""%5&7#r:c@g|]}|S))rCscalerE)rescale)r6rCrEr&r@s r8rQz2JanusImageProcessor.preprocess..Ms< 5Rc ddr:cBg|]}|S)rCmeanstdrE) normalize)r6rCr(r)rEr@s r8rQz2JanusImageProcessor.preprocess..Ss>U^oppr:c4g|]}t|S)input_channel_dim)r )r6rCrDrEs r8rQz2JanusImageProcessor.preprocess..Xs7   ej '{N_ ` ` `   r:rdata tensor_type)r!r$r%r&r'r(r)r*r+r>r"r fetch_imagesrrrHrrlogger warning_oncerr)r@rLr!r"r$r%r&r'r(r)rMr*r>r+rDrEencoded_outputss` `` ` `` ` `` r8 preprocesszJanusImageProcessor.preprocesssL"+!6IIDN '388#-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN +9+E4K^!-4;/?/K++QUQf'ttTYTU;;;""6**)&11F## :  &!)%!   A@@@@@F=vay I I   #F   $ F  #F  #F      nt   '^V,DR`aaar:rcZt||\}}|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<| 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)rrFIRSTshaper rG isinstancer5lenrHnpzerosrk enumerate) r@rCr>rDrEr.r/ num_channelsmax_dimresulticolorstarts r8rUz!JanusImageProcessor.pad_to_square`so<'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%%%-/23 r:c 4||n|j}| d|jz n|}||n|j}||n|j}||n|j}t |}t |dtjjrt|dkr|n|dS|t|d}g} |D]} t| } |r| | |||} |rK| | ||} | ddt j} |rC|rA|dkr;t%| t&j| } tj| } | | d | i} |dkr|nd}t/| | S) znApplies post-processing to the decoded image tokens by reversing transformations applied during preprocessing.Ng?r)rCr(r)rE)rWrEr4zPIL.Image.Imager_rra)r%r&r'r(r)rroPILImagerprr unnormalizerXclipastyperquint8r rLAST fromarrayappendr) r@rLr%r&r'r(r)rErMrrCrbs r8 postprocesszJanusImageProcessor.postprocesss$.#9ZZt 6D6Lt222R`'3'?||TEV #-#9ZZt !*!6IIDN )&11 fQi 1 1 < [[1__66&) ;  $ >vay I I   ' 'E"5))E ((J)_p) < U.Te ff 1c**11"(;; 3  3~AR/R/R3E;K;Pduvvv ++E22    & & & & -+9=N+N+NTX>BBBBr:cd}t|tr6t||kr"td|dt|n|g|z}t|tr6t||kr"td|dt|n|g|z}t dt ||D}t d|D}|||||}|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 VdSNr;)r6r[r\s r8r9z2JanusImageProcessor.unnormalize..s,WWytSus{WWWWWWr:c3 K|] }d|z V dS)r{Nr;)r6r\s r8r9z2JanusImageProcessor.unnormalize..s&;;#a#g;;;;;;r:rZ)rorrprHr?zipr])r@rCr(r)rErtrev_image_mean rev_image_stds r8r~zJanusImageProcessor.unnormalizes20 j( + + 5:,.. !v9=)-!%"L"L"LtCH~&"L "L % "L  "Lc5j)"L"LU5$u+#567"LE%e"456"L!"L"L "L"L"L"L"L"LP(:'A>BDH ??z?DcNC'(?% ? eC)9$9:; ? $E#/?*?$@A ? ????B%$&&%))-15%)*.'+:>9=;?)-GK!%(8(>DH!YYYD>YtCH~& Y -. Y TN Y!YtnYU5$u+#567YE%e"456Y!sJ!78Y!Y#5eCcM.B)B#CDYY&Y $E#/?*?$@A!Y" #YYY'&Y|>?>BDH HHzH U3S=%9 9:HeC)9$9:; H $E#/?*?$@A H  HHHHZ&**.'+,0+/+/(,1C1C1CTN1C! 1C tn 1C T%[) 1CDK(1C$C=1C! 1C1C1C1CpEI ++z+%%01+/0 + $E#/?*?$@A +  ++++++++r:r)'collections.abcrtypingrrnumpyrqimage_processing_utilsrrr image_transformsr r r image_utilsr rrrrrrrrrrrutilsrrrrr| get_loggerrrer__all__r;r:r8rs,%$$$$$""""""""UUUUUUUUUUSSSSSSSSSS                            _^^^^^^^^^^^JJJ  H % %SSSSS,SSSl ! !r: