sg`_dZddlmZmZmZmZmZmZddlZ ddl m Z m Z m Z mZddlmZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZm Z m!Z!m"Z"m#Z#m$Z$dd l%m&Z&e#rddl'Z'e!rddl(Z(e$jRe*Z+Gd d e Z,y) zImage processor class for Beit.)AnyDictListOptionalTupleUnionN)INIT_SERVICE_KWARGSBaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availablelogging)deprecate_kwargc&eZdZdZdgZedddeedd ejdd d ddd d d f d e d e e e fdede de e e fdee efde de deeeeefdeeeeefde dd ffd Zede e efffd Zejd d fdej.d e e e fdedeee efdeee efdej.f dZdedej.fdZ d+dede d e d e e e fdede de e e fde dede deeeeefdeeeeefdeee effd Z d+ded e d e e e fdede de e e fde dede deeeeefdeeeeefdeee efdeee efdej.fd!Z d,d"ed e d e e e fdede de e e fde deee effd#Zd-fd$ Zeddded d d d d d d d d d d d d ej@d fd%ed&eed e d e e e fdede de e e fde dede deeeeefdeeeeefdee d'eee e!fdedeee efde"jFjFf"d(Z$d-d)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 reduce_labelsdo_reduce_labelsz4.41.0)new_nameversion)extraTNgp?F do_resizesizeresampledo_center_crop crop_sizerescale_factor do_rescale do_normalize image_mean image_stdreturnc  2t |di| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_| |_y)N)heightwidthr.) param_name)super__init__r r*r+r,r-r.r0r/r1rr2rr3r&)selfr*r+r,r-r.r/r0r1r2r3r&kwargs __class__s a/var/www/html/venv/lib/python3.12/site-packages/transformers/models/beit/image_processing_beit.pyr=zBeitImageProcessor.__init__fs" "6"'tc-JT"!*!6IsUX*DZ&/&;AV 0image_processor_dictc t|j}d|vr|jd|d<t| |fi|S)z Overrides the `from_dict` method from the base class to save support of deprecated `reduce_labels` in old configs r%r&)copypopr< from_dict)clsrCr?r@s rArGzBeitImageProcessor.from_dictsK 488: 2 27K7O7OP_7` !3 4w !5@@@rBimage 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. Tr+default_to_squarer:r7r8z@The `size` argument must contain `height` and `width` keys. Got )r+r,rJrK)r ValueErrorkeysr)r>rIr+r,rJrKr?s rArzBeitImageProcessor.resizesw0TTfM 4 7$#6_`d`i`i`k_lmn n  x.$w-0#/     rBlabelcFt|}d||dk(<|dz }d||dk(<|S)Nr)r)r>rQs rA reduce_labelzBeitImageProcessor.reduce_labels6u%eqj !esl rBc|r|j|}|r|j|||| }|r|j||| }|r|j|| | }| r|j || | | }|S)N)rIr+r,rK)rIr+rK)rIscalerK)rImeanstdrK)rVr center_croprescale normalize)r>rIr&r*r+r,r-r.r0r/r1r2r3rKs rA _preprocesszBeitImageProcessor._preprocesss %%e,E KKe$]nKoE $$5yTe$fE LLuNVgLhE NNZYbsNtE rBct|}t|r|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) r&r*r+r,r-r.r0r/r1r2r3rK)input_channel_dim)rrlogger warning_oncerr^r)r>rIr*r+r,r-r.r0r/r1r2r3rJrKs rA_preprocess_imagez$BeitImageProcessor._preprocess_images$u% 5 !j   s   $ >u E   ")!)%!/!   "/{VghE rBsegmentation_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.TFrT) num_channels) rIr&r*r,r+r-r.r1r0rKr)axis) rndimrFIRSTrr^npsqueezeastypeint64) r>rdr*r+r,r-r.r&rKadded_dimensions rA_preprocess_segmentation_mapz/BeitImageProcessor._preprocess_segmentation_map s**:;  A %/ : "O 0 6 6 #O ($BCSbc$d!++"-).44,   !zz*:C +22288<rBc (t||fd|i|S)Nsegmentation_maps)r<__call__)r>imagesrrr?r@s rArszBeitImageProcessor.__call__5s wV:KVvVVrBrtrrreturn_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)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. Tr+rMr.rf)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.) r0r/r1r2r3r-r.r*r+r,) rIr*r-r0r1r,r+r/r.r2r3rJrKr$)rdr&r*r,r+r-r.labels)data tensor_type)r*r+r r,r-r.r0r/r1r2r3r&rrrOrrcrpr )r>rtrrr*r+r,r-r.r0r/r1r2r3r&rurJrKimgryrds rA preprocesszBeitImageProcessor.preprocess:s4X"+!6IDNN 'tTYYTTfM'38+9+E4K^K^!*!6IDNN !)tP[\ #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN /?/K+QUQfQf$V,  ( 34EVW X   (>O1P: F#:  &!)%!) :!   " "#-%)!-#%#'"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)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. zTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimbilinearF)r+mode align_cornersrT)logitslenrOrnumpyrangetorchnn functional interpolate unsqueezeargmaxappendshape) r>outputsr}rsemantic_segmentationidxresized_logits semantic_mapis rA"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)(__name__ __module__ __qualname____doc__model_input_namesr!rr rBICUBICboolrstrintrfloatrrr= classmethodrrGrkndarrayrrrrVr^rcrprsrjrPILImager|rr __classcell__)r@s@rAr#r#9s(T((_/A8T$+>?#'9'A'A#$(,3!:>9=!&1138n1% 1  1 S> 1c5j)111U5$u+#5671E%e"45611 1@U1@AT#s(^AA(:'A'A>BDH " zz" 38n" % " eC)9$9:; " $E#/?*?$@A "  " H*"&#'+#$( $!:>9=DH  38n  % S>U5$u+#567E%e"456$E#/?*?$@AH#'+#$( $!:>9=>BDH+++38n + % +  +S>++++U5$u+#567+E%e"456+eC)9$9:;+$E#/?*?$@A+ +`#'+#$(!%DH' $' ' 38n ' % '  ' S>' ' $E#/?*?$@A' RW _/A8T$&37#'+#$( $!:>9=+/;?(8(>(>DH#YCYC$J/YC YC 38n YC % YCYCS>YCYCYCYCU5$u+#567YCE%e"456YC#4.YC!sJ!78YC &!YC"$E#/?*?$@A#YC$ %YC'UYCv)%U )%rBr#)-rtypingrrrrrrrrkimage_processing_utilsr r r r image_transformsrr image_utilsrrrrrrrrrrrutilsrrrrrr utils.deprecationr!rr get_loggerrrar#r;rBrArsv&::jjC    1   H %G%+G%rB