rhwNdZddlZddlZddlmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z m!Z!e!jDe#Z$e rddl%Z%Gd d e Z&d gZ'y) z!Image processor class for Gemma3.N)OptionalUnion)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc&eZdZdZddgZddej ddddddddddf dedee e e fd ed ed e e e fd ed ee e ee fdee e ee fdeedeedee dee dee ddffd Z ddej"de de de dee e efdee e eff dZ ddeej"dede de de dee e efdee e effdZedddddddddej,ddddddfdedeedee e e fd ed eed ee d eed ee e ee fdee e ee fdee e efdeedee e efdeedeedee dee dee dej4j4f$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 .t|di|||nddd}t|d}||nt}||nt}||_||_||_||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_y)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 /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/gemma3/image_processing_gemma3.pyr5zGemma3ImageProcessor.__init___s" "6"'tc-JTT:#-#9Z?U !*!6I?Kc$**U5O-O"PQS^_Ka-K8+FKK ~ BB djj%#)=>?Kc$**V6P-P"QRT_`Ka-K8+FKK$))EK$789 $))F[$89:  {K (+E EI5:;5GHK!OHH5:;5GHK!OHH  0 5 5 5%.$5$56FHX$Y E5eek1155;;N3NNOK%.$5$56FHX$Y E5a!44eek>Q6QQRK IH s H 6 H0H)Himagesc g}g} |D]H} |j| |||||} |j| g| z| jt| J|| fS)N)r;r*r+r,r<r=)rUextendappendlen) r6rVr)r*r+r,r<r=pas_images_listrr; pas_imagess r9 _process_images_for_pan_and_scanz5Gemma3ImageProcessor._process_images_for_pan_and_scansz  .E**+E+E3U'"3 +J  " "E7Z#7 8   S_ - . ))r:return_tensorsc t||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|s t!dt#||||| |||| r|Dcgc] }t%|}}|Dcgc] }t'|}}|r#t)|drt*j-d| t/|d} |r|j1|||||| | \}}n|Dcgc]}d}}g}|D]k}|r|d |d }}t3|||f|| }|r|j5||| }|r|j7||| | }t9|| | }|j;|m||d}t=|| Scc}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`): 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. r!F) param_namer2zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r#r$r%r&r'r r!r"rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rVr)r*r+r,r<r=r0r1)r;r!r"r=)r;scaler=)r;meanstdr=)input_channel_dim)rr)data tensor_type)r r!rr"r#r$r%r&r'r(r)r*r+r,rr ValueErrorrr rrlogger warning_oncerr]r rescale normalizer rYr)r6rVr r!r"r#r$r%r&r'r^r<r=r(r)r*r+r,r;r_processed_imagesr0r1res r9 preprocesszGemma3ImageProcessor.preprocesssV"+!6IDNN 'tTYYTfN'38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^-<-H/dNbNb*D*P &VZVuVu #+E*P &VZVuVu # 2= /88 + *&1F#:  &!)%!  9?@nU+@F@6<vay I   $ E E /+E+E3U'"3!F! FI%++q+I+ +E $XW vuo\m 5Zk ljiSd'0{VghE  # #E *! +$!1yI>BBcA=0,sH+1H0 H5)NN)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrrArfloatlistr5npndarrayrrUr]rFIRSTrrPILImagern __classcell__)r8s@r9rr5s%N(5)-'9'B'B,3!:>9=)-*.4848>B#U#UtCH~&#U% #U  #U c5j) #U#UU5$u+#567#UE%e"456#U!#U"$#U%-SM#U%-SM#U-5UO#U !#UV?CDHPzzP%(P%( P -2 P eC)9$9:; P$E#/?*?$@APr?CDH*RZZ **%( * %( * -2 *eC)9$9:;*$E#/?*?$@A*2%&%))-'+%)*.'+:>9=;?2B2H2HDH)-*.4848>B%eCeCD>eCtCH~& eC % eC TN eC!eCtneCU5$u+#567eCE%e"456eC!sJ!78eC./eC$E#/?*?$@AeC!eC"$eC %-SM!eC"%-SM#eC$-5UO%eC& 'eC'eCr:r)(rrrIrBtypingrrnumpyrzimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrrutilsrrrr get_loggerrorhr}r__all__r3r:r9rs~( "UU    _^   H %`C-`CF " "r: