qi]BdZddlZddlmZmZmZmZddlm Z m Z ddl m Z m Z mZmZmZmZmZmZmZmZmZddlmZddlmZmZmZmZmZmZdd l m!Z!erddl"Z"erddl#Z#ejHe%Z&Gd d ed Z'e!dGddeZ(dgZ)y)zImage processor class for Beit.N)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) ImagesKwargs) TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availablelogging)requiresceZdZUdZeed<y)BeitImageProcessorKwargsak 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. do_reduce_labelsN)__name__ __module__ __qualname____doc__bool__annotations__`/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/beit/image_processing_beit.pyrr7sr'rF)total)vision)backendsc$>eZdZdZdgZeZeedde jddddddddf de d e e efdzd e d e d e e efdzd eezde de deeezdzdeeezdzde ddffd Ze jddfdej&d e e efd e de ezdzde ezdzdej&f dZdedej&fdZ d&dede dzde dzd e e efdzd e dzd e dzd e e efdzde dzd edzde dzdeeezdzdeeezdzde ezdzfdZ d&dede dzd e e efdzd e dzd e dzd e e efdzde dzd edzde dzdeeezdzdeeezdzde ezdzde ezdzdej&fdZ d'dede dzd e e efdzd e dzd e dzd e e efdzde dzde ezdzfdZd(fd Zedddddddddddddej8dfd ed!edzde dzd e e efdzd e dzd e dzd e e efdzde dzd edzde dzdeeezdzdeeezdzde dzd"e ezdzdede ezdzdej>j>f"d#Z d(d$ee!dzfd%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_stdrreturnc  2t |di| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_y)N)heightwidthr4) param_namer&)super__init__rr0r1r2r3r4r6r5r7r r8r r9r)selfr0r1r2r3r4r5r6r7r8r9rkwargs __class__s r(rBzBeitImageProcessor.__init__qs "6"'tc-JT"!*!6IsUX*DZ&/&;AV 0r'image data_formatinput_data_formatc t|dd}d|vsd|vrtd|jt|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. Tr1default_to_squarer@r=r>z@The `size` argument must contain `height` and `width` keys. Got )r1r2rGrH)r ValueErrorkeysr)rCrFr1r2rGrHrDs r(rzBeitImageProcessor.resizesw0TTfM 4 7$#6_`d`i`i`k_lmn n  x.$w-0#/     r'labelcFt|}d||dk(<|dz }d||dk(<|S)Nr)r)rCrNs r( reduce_labelzBeitImageProcessor.reduce_labels6u%eqj !esl r'c|r|j|}|r|j|||| }|r|j||| }|r|j|| | }| r|j || | | }|S)N)rFr1r2rH)rFr1rH)rFscalerH)rFmeanstdrH)rSr center_croprescale normalize)rCrFrr0r1r2r3r4r6r5r7r8r9rHs r( _preprocesszBeitImageProcessor._preprocesss %%e,E KKe$]nKoE $$5yTe$fE LLuNVgLhE NNZYbsNtE r'ct|}|r t|rtjd| t |} |j |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.F) rr0r1r2r3r4r6r5r7r8r9rH)input_channel_dim)rrlogger warning_oncerr[r )rCrFr0r1r2r3r4r6r5r7r8r9rGrHs r(_preprocess_imagez$BeitImageProcessor._preprocess_images$u% /%0   s   $ >u E   ")!)%!/!   "/{VghE r'segmentation_mapc Nt|}|jdk(r|d}d} tj}nd} | t |d}|j |||||||ddtj }| rt j|d }|jt j}|S) z'Preprocesses a single segmentation map.)N.TFrQ) num_channels) rFrr0r2r1r3r4r7r6rHr)axis) rndimr FIRSTrr[npsqueezeastypeint64) rCrar0r1r2r3r4rrHadded_dimensions r(_preprocess_segmentation_mapz/BeitImageProcessor._preprocess_segmentation_map s**:;  A %/ : "O 0 6 6 #O ($BCSbc$d!++"-).44,   !zz*:C +22288<r'c (t||fd|i|S)Nsegmentation_maps)rA__call__)rCimagesrorDrEs r(rpzBeitImageProcessor.__call__5s wV:KVvVVr'rqroreturn_tensorsc8||n |j}||n |j}t|dd}||n |j}||n |j}||n |j }t|dd}||n |j }| | n |j} | | n |j} | | n |j} | | n |j} | | n |j} t|}| t|d}|t|s tdt|s tdt|| | | | ||||| |Dcgc] }|j!||||| ||| || | || "}}d |i}|*|Dcgc]}|j#|| ||||| }}||d <t%||Scc}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`. 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.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. Tr1rJr4rc)expected_ndimsz_Invalid segmentation_maps type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.TensorzSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor) r6r5r7r8r9r3r4r0r1r2) rFr0r3r6r7r2r1r5r4r8r9rGrHr.)rarr0r2r1r3r4labels)data tensor_type)r0r1rr2r3r4r6r5r7r8r9rrrrLrr`rmr)rCrqror0r1r2r3r4r6r5r7r8r9rrrrGrHimgrvras r( preprocesszBeitImageProcessor.preprocess:s*R"+!6IDNN 'tTYYTTfM'38+9+E4K^K^!*!6IDNN !)tP[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN /?/K+QUQfQf)&1  ( 89J[\ ]   (>O1Pq F#rs s%!)%!) :!   " "#-%)!-#%#'"3 #   &'  (): !%11%5%5'%#1'2 !  !/DN>BBI , !s .%FF target_sizesc&|j}|t|t|k7r tdt|r|j }g}t t|D]k}t jjj||jd||dd}|djd}|j|m|S|jd}t |jdDcgc]}|| }}|Scc}w)a Converts the output of [`BeitForSemanticSegmentation`] into semantic segmentation maps. 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. zTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimbilinearF)r1mode align_cornersrQ)logitslenrLrnumpyrangetorchnn functional interpolate unsqueezeargmaxappendshape) rCoutputsrzrsemantic_segmentationidxresized_logits semantic_mapis r("post_process_semantic_segmentationz5BeitImageProcessor.post_process_semantic_segmentations(   #6{c,// j|,+113 $& !S[) ;!&!4!4!@!@3K))a)0|C7Hzin"A" .a077A7> %,,\:  ;%$%+MMaM$8 !GLMbMhMhijMkGl$m!%:1%=$m !$m$$%ns> D) NNNNNNNNNNNN)NNNNNNN)N)$r r!r"r#model_input_namesr valid_kwargsrrrBICUBICr$dictstrintfloatlistrBrhndarrayr rr rSr[r`rmrprgrPILImagerytupler __classcell__)rEs@r(r-r-Bs(T((+L$+>?&*'9'A'A#+/&-!1504!&1138nt#1% 1  1 S>D( 1e 111DK'$.14;&-11 1@1H(:'A'A59;? " zz" 38n" % " ++d2 " !11D8 "  " H*)-!%&*.2&*+/"&'+$(1504;?+$;  38nt#  %t+ t S>D(4K TkDK'$.4;&-!11D8H"&&*.2&*+/"&'+$(150459;?++$;+38nt# + %t+ + t +S>D(+4K+ +Tk+DK'$.+4;&-+++d2+!11D8+ +`"&&*.2&*+/(,;?' $' $;' 38nt# ' %t+ ' t ' S>D(' +' !11D8' RW %&04!%&*.2&*+/"&'+$(1504(,26(8(>(>;?#SCSC&,SC$; SC 38nt# SC %t+ SCt SCS>D(SC4KSC SCTkSCDK'$.SC4;&-SC+SCj(4/SC &!SC"!11D8#SC$ %SC'SCj(%U VZHZ(%r'r-)*r#rrhimage_processing_utilsrrrrimage_transformsrr image_utilsr r r r rrrrrrrprocessing_utilsrutilsrrrrrrutils.import_utilsrrr get_loggerr r^rr-__all__r&r'r(rs&jjC    -+   H %|5 ;u%+u% u%p r'