`iNdZddlZddlZddlmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z m!Z!e!j"e#Z$e rddl%Z%Gd d e Z&d gZ'dS) z!Image processor class for Gemma3.N)OptionalUnion)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc&eZdZdZddgZddejddddddddddf dedee e e fd ed ed e e e fd ed ee e ee fdee e ee fdeedeedee dee dee ddffd Z ddejde de de dee e efdee e eff dZ ddeejdede de de dee e efdee e effdZedddddddddejddddddfdedeedee e e fd eed eed ee d eed ee e ee fdee e ee fdee e efdeedee e efdeedeedee dee dee dejjf$dZxZS)Gemma3ImageProcessoraI Constructs a SigLIP 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 `do_resize` in the `preprocess` method. size (`dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after resizing. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` 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 by the specified mean and standard deviation. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `[0.5, 0.5, 0.5]`): 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 `[0.5, 0.5, 0.5]`): 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_pan_and_scan (`bool`, *optional*): Whether to apply `pan_and_scan` to images. pan_and_scan_min_crop_size (`int`, *optional*): Minimum size of each crop in pan and scan. pan_and_scan_max_num_crops (`int`, *optional*): Maximum number of crops per image in pan and scan. pan_and_scan_min_ratio_to_activate (`float`, *optional*): Minimum aspect ratio to activate pan and scan. pixel_values num_cropsTNgp? do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbdo_pan_and_scanpan_and_scan_min_crop_sizepan_and_scan_max_num_crops"pan_and_scan_min_ratio_to_activatereturnc Ptjdi|||nddd}t|d}||nt}||nt}||_||_||_||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_dS)N)heightwidthT)default_to_square)super__init__rr r r r!r"r#r$r%r&r'r(r)r*r+r,)selfr r!r"r#r$r%r&r'r(r)r*r+r,kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/gemma3/image_processing_gemma3.pyr5zGemma3ImageProcessor.__init___s" ""6"""'ttc-J-JTT:::#-#9ZZ?U !*!6IIz5Gemma3ImageProcessor.pan_and_scan..HHHK!OHHHr:cg|]}|zSr3r3)rBrC crop_size_hs r9rEz5Gemma3ImageProcessor.pan_and_scan..rFr:c>g|]\}}||z||zfSr3r3rBpos_hpos_wrHrDr;s r9rEz5Gemma3ImageProcessor.pan_and_scan..sK E5eek1155;;N3NNOr:cDg|]\}}dd||z||zfS)Nr3rJs r9rEz5Gemma3ImageProcessor.pan_and_scan..sQ E5aaa!44eek>Q6QQRr:) rintmathfloorminmaxceilrangerLAST itertoolsproduct)r6r;r*r+r,r<r=r0r1 num_crops_w num_crops_hcrop_positions_wcrop_positions_h image_cropsrHrDs ` @@r9 pan_and_scanz!Gemma3ImageProcessor.pan_and_scanse6'u--  F??v~ BBB dj#)=>>??Kc$*U5O-O"P"PQQS^__Ka--K8+FFKKK ~ BBB dj%#)=>>??Kc$*V6P-P"Q"QRRT_``Ka--K8+FFKK$)EK$78899 $)F[$899::  {K ( (+E E EIHHHHU;5G5GHHHHHHHU;5G5GHHH  0 5 5 5$-$56FHX$Y$YKK $-$56FHX$Y$YK r:imagesc g}g} |D]X} || |||||} || g| z| t| Y|| fS)N)r;r*r+r,r<r=)r]extendappendlen) r6r^r)r*r+r,r<r=pas_images_listrr; pas_imagess r9 _process_images_for_pan_and_scanz5Gemma3ImageProcessor._process_images_for_pan_and_scans  . .E**+E+E3U'"3 +J  " "E7Z#7 8 8 8   S__ - - - - ))r:return_tensorsc V||n|j}||n|j}t|dd}||n|j}||n|j}||n|j}||n|j}||n|j}| | n|j} | | n|j } ||n|j }||n|j }||n|j }||n|j }||}t|}t!|st#dt%||||| |||| r d|D}d|D}|r/t'|d rt(d | t-|d } |r ||||||| | \}}n d |D}g}|D]}|r%|d |d}}t1|||f|| }|r|||| }|r|||| | }t7|| | }||||d}t;|| 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`): Size of the image after resizing. 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_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`. 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. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. do_pan_and_scan (`bool`, *optional*, defaults to `self.do_pan_and_scan`): Whether to apply `pan_and_scan` to images. pan_and_scan_min_crop_size (`int`, *optional*, defaults to `self.pan_and_scan_min_crop_size`): Minimum size of each crop in pan and scan. pan_and_scan_max_num_crops (`int`, *optional*, defaults to `self.pan_and_scan_max_num_crops`): Maximum number of crops per image in pan and scan. pan_and_scan_min_ratio_to_activate (`float`, *optional*, defaults to `self.pan_and_scan_min_ratio_to_activate`): Minimum aspect ratio to activate pan and scan. Nr!F) param_namer2zkInvalid 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|Sr3)r rBr;s r9rEz3Gemma3ImageProcessor.preprocess..es @@@nU++@@@r:c,g|]}t|Sr3)rrjs r9rEz3Gemma3ImageProcessor.preprocess..hs <<.s+++q+++r:r0r1)r;r!r"r=)r;scaler=)r;meanstdr=)input_channel_dim)rr)data tensor_type)r r!rr"r#r$r%r&r'r(r)r*r+r, fetch_imagesrr ValueErrorrrlogger warning_oncerrer rescale normalizer rar)r6r^r r!r"r#r$r%r&r'rfr<r=r(r)r*r+r,rprocessed_imagesr;r0r1rrs r9 preprocesszGemma3ImageProcessor.preprocesssHV"+!6IIDN 'ttTYTfNNN'388#-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN +9+E4K^-<-H//dNb*D*P & &VZVu #+E*P & &VZVu # 2= / .8 + ""6**)&11F## :  &!)%!   A@@@@@F=vay I I   , $ E E /+E+E3U'"3!F!! FII,+F+++I + +E  $XW vuo\m m 5Zk ll jiSd'0{VghhhE  # #E * * * * 0yII>BBBBr:)NN)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrrNrfloatlistr5npndarrayrr]rerFIRSTrrPILImager{ __classcell__)r8s@r9rr5s^%%N(5)-'9'B,3!:>9=)-*.4848>B#U#U#UtCH~&#U% #U  #U c5j) #U#UU5$u+#567#UE%e"456#U!#U"$#U%-SM#U%-SM#U-5UO#U !#U#U#U#U#U#UV?CDHPPzP%(P%( P -2 P eC)9$9:; P$E#/?*?$@APPPPr?CDH**RZ **%( * %( * -2 *eC)9$9:;*$E#/?*?$@A****2%$&&%))-15%)*.'+:>9=;?2B2HDH)-*.4848>B%fCfCfCD>fCtCH~& fC -. fC TN fC!fCtnfCU5$u+#567fCE%e"456fC!sJ!78fC./fC$E#/?*?$@AfC!fC"$fC %-SM!fC"%-SM#fC$-5UO%fC& 'fCfCfC'&fCfCfCfCfCr:r)(rrVrOtypingrrnumpyrimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrrutilsrrrr get_loggerr|rvrr__all__r3r:r9rs(' """"""""UUUUUUUUUU                            _^^^^^^^^^^^  H % %JJJaCaCaCaCaC-aCaCaCH " "r: