sgS dZddlmZmZmZmZmZddlZddl m Z m Z m Z ddl mZmZmZmZddlmZmZmZmZmZmZmZmZmZddlmZmZmZm Z m!Z!m"Z"e!rddl#Z#erddl$Z$e"jJe&Z'Gd d e Z(y) z$Image processor class for MobileViT.)DictListOptionalTupleUnionN)BaseImageProcessor BatchFeature get_size_dict)flip_channel_orderget_resize_output_image_sizeresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availableloggingceZdZdZdgZddej dddddfdedee e fded ed e e e fd ed ee e fd eddffd Z ej ddfdejdee e fdedee e efdee e efdejf dZ d dejdee e efdee e efdejfdZd!fd Z d"deded ed ed edeee e fded ee d eee e fdee e effdZ d#dededee e fded ed e d ed ee e fd edee e efdee e efdejfdZ d"dededee e fd ed ee e fdee e efdejfdZeddddddddddej4df dedeededee e fded ed e d ed ee e fd edee e efdedee e efdej:j:fdZd!dee fdZ!xZ"S)$MobileViTImageProcessora$ Constructs a MobileViT 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 `{"shortest_edge": 224}`): Controls the size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Defines the resampling filter to use if resizing the image. Can be overridden by the `resample` 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. 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_center_crop (`bool`, *optional*, defaults to `True`): Whether to crop the input at the center. 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": 256, "width": 256}`): Desired output size `(size["height"], size["width"])` when applying center-cropping. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_flip_channel_order (`bool`, *optional*, defaults to `True`): Whether to flip the color channels from RGB to BGR. Can be overridden by the `do_flip_channel_order` parameter in the `preprocess` method. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factordo_center_crop crop_sizedo_flip_channel_orderreturnc  t |d i| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ y) N shortest_edgeFdefault_to_square)heightwidthr( param_name) super__init__r r"r#r$r%r&r'r(r)) selfr"r#r$r%r&r'r(r)kwargs __class__s k/var/www/html/venv/lib/python3.12/site-packages/transformers/models/mobilevit/image_processing_mobilevit.pyr7z MobileViTImageProcessor.__init__Xs "6"'tos-CTU;!*!6IsUXr?) ValueErrorr r) r8r=r#r$r>r?r9r/ output_sizes r;rzMobileViTImageProcessor.resizets2! d "(D %   'T/NDM2D`a a2 //    #/     r<ct|||S)a Flip the color channels from RGB to BGR or vice versa. Args: image (`np.ndarray`): The image, represented as a numpy array. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. )r>r?)r )r8r=r>r?s r;r z*MobileViTImageProcessor.flip_channel_orders""%[Teffr<c (t||fd|i|S)z Preprocesses a batch of images and optionally segmentation maps. Overrides the `__call__` method of the `Preprocessor` class so that both images and segmentation maps can be passed in as positional arguments. segmentation_maps)r6__call__)r8imagesrEr9r:s r;rFz MobileViTImageProcessor.__call__s wV:KVvVVr<c |r|j|||| }|r|j||| }|r|j|| | }|r|j|| }|S)N)r=r#r$r?)r=scaler?)r=r#r?)r?)rrescale center_cropr ) r8r=r"r%r'r)r#r$r&r(r?s r; _preprocessz#MobileViTImageProcessor._preprocessso KKe$]nKoE LLuNVgLhE $$5yTe$fE ++EEV+WE r<c t|}t|r|rtjd| t |} |j ||||||||| |  }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.) r=r"r#r$r%r&r'r(r)r?)input_channel_dim)rrlogger warning_oncerrLr) r8r=r"r#r$r%r&r'r(r)r>r?s r;_preprocess_imagez)MobileViTImageProcessor._preprocess_images u% 5 !j   s   $ >u E   !))"7/!  ,E;Rcd r<segmentation_mapc @t|}|jdk(rd}|d}tj}nd}| t |d}|j |||t jd||d| }|r|jd}|jtj}|S) zPreprocesses a single mask.T)N.F) num_channels) r=r"r#r$r%r'r(r)r?r) rndimrFIRSTrrLrNEARESTsqueezeastypenpint64)r8rRr"r#r'r(r?added_channel_dims r;_preprocess_maskz(MobileViTImageProcessor._preprocess_masks**:;  A % $ / :  0 6 6  %  ($BCSbc$d!++"'//)"'/,   /77: +22288<r<rGrEreturn_tensorsc||n |j}||n |j}||n |j}||n |j}||n |j}| | n |j } ||n |j }t|d}| | n |j} t| d} t|}| t|d}t|}t|s td|t|s tdt|||| ||| |Dcgc]}|j|||||||| | | |  }}d |i}|)|Dcgc]}|j||||| | }}||d <t|| Scc}wcc}w)aj 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 map to preprocess. 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 by rescale factor. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` 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 center crop if `do_center_crop` is set to `True`. do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`): Whether to flip the channel order of the image. 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. 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. Fr.r(r3rT)expected_ndimszkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zvInvalid segmentation map 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#r$r%r&r'r(r)r>r?r!)rRr"r#r'r(r?labels)data tensor_type)r"r$r%r&r'r)r#r r(rrrArrQr_r )r8rGrEr"r#r$r%r&r'r(r)r`r>r?imgrdrRs r; preprocessz"MobileViTImageProcessor.preprocess,sz"+!6IDNN '38#-#9Zt +9+E4K^K^+9+E4K^K^%:%F !DLfLf 'tTYYTU;!*!6IDNN !) D $V,  ( 34EVW X $V,F#:   (>O1P:  &!)) 0   " "#!%--#&;'"3 #   "'  (): !%%%%5'#1'&7 & !  !/DN>BBE ( !s #E%3E* 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 [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch. Args: outputs ([`MobileViTForSemanticSegmentation`]): 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_cornersrU)logitslenrArnumpyrangetorchnn functional interpolate unsqueezeargmaxappendshape) r8outputsrhrnsemantic_segmentationidxresized_logits semantic_mapis r;"post_process_semantic_segmentationz:MobileViTImageProcessor.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)NN)N)NNNNN) NNNNNNNNNN)#__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrstrintrfloatr7r\ndarrayrrrr rFrrLrQr_rrXrPILImagergrrr __classcell__)r:s@r;r r 6s>((#'9'B'B,3#$(&*;;38n;% ;  ; c5j) ;;S>; $; ;@(:'B'B>BDH / zz/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / h?CDH gzzgeC)9$9:;g$E#/?*?$@A g  g&W *.'+*..2DH    $ tCH~&%!DcN+$E#/?*?$@A<#'+ $#$(&*>BDH(((38n ( % (  (((S>( $(eC)9$9:;($E#/?*?$@A( (Z##$(DH$ $$ $ 38n $  $ S> $ $E#/?*?$@A$  $ L%&37#'+ $#$(&*;?(8(>(>DHICIC$J/IC IC 38n IC % ICICICICS>IC $IC!sJ!78IC&IC$E#/?*?$@AIC IC'ICX)%U )%r<r ))rtypingrrrrrrpr\image_processing_utilsr r r image_transformsr r rr image_utilsrrrrrrrrrutilsrrrrrrrrr get_loggerrrOr r5r<r;rso+55UUuu      H %l%0l%r<