o Zh%U@sdZddlmZmZmZmZmZddlZddl m Z m Z m Z ddl mZmZmZmZddlmZmZmZmZmZmZmZmZmZddlmZmZmZm Z m!Z!m"Z"dd l#m$Z$e!r]ddl%Z%erdddl&Z&e"'e(Z)e$d d Gd d d e Z*d gZ+dS)z$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_availablelogging)requires)Zvision)backendscs>eZdZdZdgZddejdddddfdedee e e fded ed e e e fd ed ee e e fd eddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZ  d)dejdee e efdee e efdejfddZd*fdd Z     d+deded ed ed edee e e fded ee d ee e e fdee e effddZ          d,dedeedee e e fded eed ee d eed ee e e fd eedee e efdee e efdejfddZ     d+dedeedee e e fd eed ee e e fdee e efdejfdd Zeddddddddddejdf d!ed"eedeedee e e fded eed ee d eed ee e e fd eed#ee e efdedee e efdejjfd$d%Zd*d&eee fd'd(Z!Z"S)-MobileViTImageProcessora$ 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  stjd i| |dur|nddi}t|dd}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ dS) 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__r4g/var/www/auris/lib/python3.10/site-packages/transformers/models/mobilevit/image_processing_mobilevit.pyr6Zs    z MobileViTImageProcessor.__init__image data_formatinput_data_formatc Ksnd}d|vr |d}d}nd|vrd|vr|d|df}ntdt||||d}t|f||||d|S) a[ Resize an image. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): 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 (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Tr+Fr0r1zASize must contain either 'shortest_edge' or 'height' and 'width'.)r#r.r>)r#r$r=r>) ValueErrorr r ) r7r<r#r$r=r>r8r.Z output_sizer4r4r;r vs.zMobileViTImageProcessor.resizecCst|||dS)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 )r7r<r=r>r4r4r;r sz*MobileViTImageProcessor.flip_channel_orderc stj|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)r5__call__)r7imagesr@r8r9r4r;rAsz MobileViTImageProcessor.__call__c CsT|r |j|||| d}|r|j||| d}|r|j|| | d}|r(|j|| d}|S)N)r<r#r$r>)r<scaler>)r<r#r>)r>)r ZrescaleZ center_cropr ) r7r<r"r%r'r)r#r$r&r(r>r4r4r; _preprocesss z#MobileViTImageProcessor._preprocessc Cs^t|}|rt|rtd| durt|} |j||||||||| | d }t|| | d}|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.N) r<r"r#r$r%r&r'r(r)r>)Zinput_channel_dim)rrloggerZ warning_oncerrDr) r7r<r"r#r$r%r&r'r(r)r=r>r4r4r;_preprocess_images*  z)MobileViTImageProcessor._preprocess_imagesegmentation_mapc Cszt|}|jdkrd}|d}tj}n d}|durt|dd}|j|||tjd||d|d }|r5|d }| t j }|S) zPreprocesses a single mask.T)N.FN)Z num_channels) r<r"r#r$r%r'r(r)r>r) rndimrFIRSTrrDrZNEARESTZsqueezeZastypenpZint64)r7rGr"r#r'r(r>Zadded_channel_dimr4r4r;_preprocess_masks.    z(MobileViTImageProcessor._preprocess_maskrBr@return_tensorsc spdurn jdurn jdurn jdur!n jdur*n jdur3n j dur< n j t dd durKn jtddt |}|durbt |dd}t |}t |snt d|durzt |szt d t  d  f d d |D}d |i}|dur fdd |D}||d<t || dS)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. NFr-r(r2rH)Zexpected_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$cs,g|]} j| d qS)) r<r"r#r$r%r&r'r(r)r=r>)rF).0Zimg r(r=r'r)r%r"r>r$r&r7r#r4r; s z6MobileViTImageProcessor.preprocess..r!c s"g|] }j|dqS))rGr"r#r'r(r>)rM)rOrG)r(r'r"r>r7r#r4r;rQs labels)dataZ tensor_type)r"r$r%r&r'r)r#r r(rrr?rr )r7rBr@r"r#r$r%r&r'r(r)rNr=r>rSr4rPr; preprocess.sT=      z"MobileViTImageProcessor.preprocess target_sizescs|j}|durHt|t|krtdt|r|}gtt|D]"}tjjj ||j dd||ddd}|dj dd} |q#S|j ddfd d tj dDS) 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. NzTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimZbilinearF)r#modeZ align_cornersrIcsg|]}|qSr4r4)rOiZsemantic_segmentationr4r;rQszNMobileViTImageProcessor.post_process_semantic_segmentation..)logitslenr?rnumpyrangetorchnnZ functionalZ interpolateZ unsqueezeZargmaxappendshape)r7ZoutputsrUrZidxZresized_logitsZ semantic_mapr4rYr;"post_process_semantic_segmentations&  z:MobileViTImageProcessor.post_process_semantic_segmentation)NN)N)NNNNN) NNNNNNNNNN)#__name__ __module__ __qualname____doc__Zmodel_input_namesrZBILINEARboolrrstrintrfloatr6rLZndarrayrr r rArrDrFrMrrKrPILZImagerTrrrc __classcell__r4r4r9r;r 7sn      4         - &       r ),rgtypingrrrrrr\rLZimage_processing_utilsrr r Zimage_transformsr r r rZ image_utilsrrrrrrrrrutilsrrrrrrZutils.import_utilsrrlr^Z get_loggerrdrEr __all__r4r4r4r;s&,   2