`iA^HdZddlmZmZddlZddlmZmZm Z m Z ddl m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZmZm Z dd l!m"Z"erddl#Z#erddl$Z$e j%e&Z'e"d Gd d eZ(d gZ)dS)zImage processor class for Beit.)OptionalUnionN)INIT_SERVICE_KWARGSBaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availablelogging)requires)vision)backendsc%ReZdZdZdgZeeddejddddddddf de d e e e e fd ed e d e e e e fd ee efde de de eeeefde eeeefde ddffd Zejddfdejd e e e fd ede ee efde ee efdejf dZdedejfdZ d&dede e de e d e e e e fd e ed e e d e e e e fde e d e ede e de eeeefde eeeefde ee effdZ d&dede e d e e e e fd e ed e e d e e e e fde e d e ede e de eeeefde eeeefde ee efde ee efdejfdZ d'dede e d e e e e fd e ed e e d e e e e fde e de ee effdZd(fd Zedddddddddddddejdfd ed!e ede e d e e e e fd e ed e e d e e e e fde e d e ede e de eeeefde eeeefde e d"e ee efdede ee efdejjf"d#Z d(d$e ee!fd%Z"xZ#S))BeitImageProcessoraK Constructs a BEiT 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[str, int]` *optional*, defaults to `{"height": 256, "width": 256}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`): Desired output size when applying center-cropping. Only has an effect if `do_center_crop` is set to `True`. Can be overridden by the `crop_size` parameter 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 the `rescale_factor` 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. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): The mean to use if normalizing the image. This is a float or list of floats of length of the number of channels of the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): The standard deviation to use if normalizing the image. This is a float or list of floats of length of the number of channels of the image. Can be overridden by the `image_std` parameter in the `preprocess` method. do_reduce_labels (`bool`, *optional*, defaults to `False`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. Can be overridden by the `do_reduce_labels` parameter in the `preprocess` method. pixel_values)extraTNgp?F do_resizesizeresampledo_center_crop crop_sizerescale_factor do_rescale do_normalize image_mean image_stddo_reduce_labelsreturnc  \tjdi| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_dS)N)heightwidthr() param_name)super__init__r r$r%r&r'r(r*r)r+r r,r r-r.)selfr$r%r&r'r(r)r*r+r,r-r.kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/beit/image_processing_beit.pyr8zBeitImageProcessor.__init__gs ""6"""'ttc-J-JT""!*!6IIsUX**DZ&/&;AV 0image data_formatinput_data_formatc t|dd}d|vsd|vr$td|t|f|d|df|||d|S)a Resize an image to (size["height"], size["width"]). Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PIL.Image.BICUBIC`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Tr%default_to_squarer5r2r3z@The `size` argument must contain `height` and `width` keys. Got )r%r&r?r@)r ValueErrorkeysr )r9r>r%r&r?r@r:s r<r zBeitImageProcessor.resizes0TTfMMM 4  7$#6#6m`d`i`i`k`kmmnn n  x.$w-0#/       r=labelcRt|}d||dk<|dz }d||dk<|S)Nr)r)r9rFs r< reduce_labelzBeitImageProcessor.reduce_labels9u%%eqj !esl r=c|r||}|r||||| }|r|||| }|r||| | }| r||| | | }|S)N)r>r%r&r@)r>r%r@)r>scaler@)r>meanstdr@)rKr center_croprescale normalize)r9r>r.r$r%r&r'r(r*r)r+r,r-r@s r< _preprocesszBeitImageProcessor._preprocesss  -%%e,,E  pKKe$]nKooE  g$$5yTe$ffE  iLLuNVgLhhE  uNNZYbsNttE r=ct|}|r)t|rtd| t |} ||d|||||||| | | |  }| t || | }|S)zPreprocesses a single image.zIt 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.NF) r.r$r%r&r'r(r*r)r+r,r-r@)input_channel_dim)rrlogger warning_oncerrSr )r9r>r$r%r&r'r(r*r)r+r,r-r?r@s r<_preprocess_imagez$BeitImageProcessor._preprocess_images$u%%  /%00    s     $ >u E E   ")!)%!/!    "/{VghhhE r=segmentation_mapc Rt|}|jdkr|d}d} tj}nd} |t |d}||||||||ddtj }| rt j|d }|t j }|S) z'Preprocesses a single segmentation map.)N.TFNrI) num_channels) r>r.r$r&r%r'r(r+r*r@r)axis) rndimrFIRSTrrSnpsqueezeastypeint64) r9rYr$r%r&r'r(r.r@added_dimensions r<_preprocess_segmentation_mapz/BeitImageProcessor._preprocess_segmentation_maps**:;;  A % %/ : "O 0 6  #O ($BCSbc$d$d$d!++"-).4,     D!z*:CCC +2228<<r=c <tj|fd|i|S)Nsegmentation_maps)r7__call__)r9imagesrgr:r;s r<rhzBeitImageProcessor.__call__+s* uwwVV:KVvVVVr=rirgreturn_tensorsc  njnjtddnjnjnjtddnj  nj  nj  nj  nj  nj t|}|t|d}|t|stdt|std t     f d |D}d |i}| fd |D}||d<t!||S)aI 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`. segmentation_maps (`ImageInput`, *optional*) Segmentation maps 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_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image. crop_size (`dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the image after center crop. If one edge the image is smaller than `crop_size`, it will be padded with zeros and then cropped 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. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. do_reduce_labels (`bool`, *optional*, defaults to `self.do_reduce_labels`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. 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. NTr%rBr(r[)expected_ndimszwInvalid segmentation_maps type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zkInvalid 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$r%r&cT g|]$} |    %S)) r>r$r'r*r+r&r%r)r(r,r-r?r@)rX).0imgr(r?r'r+r*r$r,r-r@r&r)r9r%s r< z1BeitImageProcessor.preprocess..sg     " "#-%)!-#%#'"3 #     r=r"c Hg|]}|S))rYr.r$r&r%r'r()re) rnrYr(r'r.r$r&r9r%s r<rpz1BeitImageProcessor.preprocess..sU ! ! !%11%5%5'%#1'2 ! ! !r=labels)data tensor_type)r$r%r r&r'r(r*r)r+r,r-r.rrrDrr)r9rirgr$r%r&r'r(r*r)r+r,r-r.rjr?r@rss` ``````````` `` r< preprocesszBeitImageProcessor.preprocess0sV"+!6IIDN 'ttTYTTfMMM'388+9+E4K^!*!6IIDN !)tP[\\\ #-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN /?/K++QUQf)&11  ( 89J[\ ] ] ]   (>O1P1P (: F## :  &!)%!)                 !   &'  ( ! ! ! ! ! ! ! ! ! !): ! ! ! /DN>BBBBr= target_sizescl|j}|t|t|krtdt|r|}gt t|D]{}t jj || d||dd}|d d} ||n<| dfd t j dDS) a6 Converts the output of [`BeitForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch. Args: outputs ([`BeitForSemanticSegmentation`]): Raw outputs of the model. target_sizes (`list[Tuple]` of length `batch_size`, *optional*): List of tuples corresponding to the requested final size (height, width) of each prediction. If unset, predictions will not be resized. Returns: semantic_segmentation: `list[torch.Tensor]` of length `batch_size`, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if `target_sizes` is specified). Each entry of each `torch.Tensor` correspond to a semantic class id. NzTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimbilinearF)r%mode align_cornersrIc g|] }| Sr6r6)rnisemantic_segmentations r<rpzIBeitImageProcessor.post_process_semantic_segmentation..s$m$m$m!%:1%=$m$m$mr=)logitslenrDrnumpyrangetorchnn functional interpolate unsqueezeargmaxappendshape)r9outputsrvridxresized_logits semantic_mapr~s @r<"post_process_semantic_segmentationz5BeitImageProcessor.post_process_semantic_segmentationsM"  #6{{c,//// j|,, 4+1133 $& !S[[)) ; ;!&!4!@!@3K))a)00|C7Hzin"A"" .a077A7>> %,,\::::  ;%+MMaM$8$8 !$m$m$m$muMbMhijMkGlGl$m$m$m !$$r=) NNNNNNNNNNNN)NNNNNNN)N)$__name__ __module__ __qualname____doc__model_input_namesrrrBICUBICboolrdictstrintrfloatlistr8r`ndarrayrr rrKrSrXrerhr_rPILImagerutupler __classcell__)r;s@r<r!r!9sE((T(($$+>???)-'9'A#.2,3!:>9=!&111tCH~&1% 1  1 DcN+ 1c5j)111U5$u+#5671E%e"45611 11111@?1H(:'A>BDH " " z" 38n" % " eC)9$9:; " $E#/?*?$@A "  " " " " H*,0$()-15)-.2%)*.'+:>9=DH#4.D>  tCH~&  -. !DcN+TN!tnU5$u+#567E%e"456$E#/?*?$@AH%))-15)-.2%)*.'+:>9=>BDH+++D>+tCH~& + -. + ! +DcN++TN+!+tn+U5$u+#567+E%e"456+eC)9$9:;+$E#/?*?$@A+ ++++`%))-15)-.2+/DH' ' $' D>' tCH~& ' -. ' ! ' DcN+' #4.' $E#/?*?$@A' ' ' ' RWWWWWW %$&&37$()-15)-.2%)*.'+:>9=+/;?(8(>DH#YCYCYC$J/YCD> YC tCH~& YC -. YC!YCDcN+YCTNYC!YCtnYCU5$u+#567YCE%e"456YC#4.YC!sJ!78YC &!YC"$E#/?*?$@A#YC$ %YCYCYC'&YCv)%)%QUV[Q\H])%)%)%)%)%)%)%)%r=r!)*rtypingrrrr`image_processing_utilsrrrr image_transformsr r image_utilsr r rrrrrrrrrutilsrrrrrrutils.import_utilsrrr get_loggerrrVr!__all__r6r=r<rs&%""""""""jjjjjjjjjjjjCCCCCCCC                          +*****JJJLLL  H % % ;{%{%{%{%{%+{%{% {%| r=