o ei( @sddlZddlmZddlmZmZddlZddlmZddl m Z ddl m Z m Z ddlmZmZmZmZdd lmZmZmZd d lmZd d lmZerTddlmZddlmmm Z!ddde"ee"Bde#de"def ddZ$eGdddeZ%dgZ&dS)N)Iterable) TYPE_CHECKINGOptional) BatchFeature)BaseImageProcessorFast)group_images_by_shapereorder_images)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDPILImageResamplingSizeDict) TensorTypeauto_docstringrequires_backends)BeitImageProcessorFast)DPTImageProcessorKwargs)DepthEstimatorOutput input_image torch.Tensor output_sizekeep_aspect_ratiomultiplereturnc Csddd}|jdd\}}|\}}||} ||} |r-td| td| kr+| } n| } || ||d} || ||d} t| | dS) NrcSsPt|||}|dur||krt|||}||kr&t|||}|SN)roundmathfloorceil)valrmin_valmax_valxr%a/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/dpt/modular_dpt.pyconstrain_to_multiple_of4s z>get_resize_output_image_size..constrain_to_multiple_ofr)rheightwidth)rN)shapeabsr ) rrrrr' input_height input_width output_height output_width scale_height scale_width new_height new_widthr%r%r&get_resize_output_image_size.s   r6c&@sjeZdZejZeZeZ dddZ dZ dZ dZ dZdZdZdZdZdZdZeZ    d*dd d ed ed d ededBdedd fddZ d+dd dedd fddZded deded ed ed dedededededeeeBdBdeeeBdBdededBd ededBd!edBd"ee BdBde!f&d#d$Z" d,d%d&d'e ee#eefBdBdBdee$ee ffd(d)Z%dS)-DPTImageProcessorFastir)TFgp?rNimagersize interpolationztvF.InterpolationMode antialiasensure_multiple_ofrrcCsJ|jr|jstd|t||j|jf||d}tj|||||dS)a< Resize an image to `(size["height"], size["width"])`. Args: image (`torch.Tensor`): Image to resize. size (`SizeDict`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. interpolation (`InterpolationMode`, *optional*, defaults to `InterpolationMode.BILINEAR`): `InterpolationMode` filter to use when resizing the image e.g. `InterpolationMode.BICUBIC`. antialias (`bool`, *optional*, defaults to `True`): Whether to use antialiasing when resizing the image ensure_multiple_of (`int`, *optional*): If `do_resize` is `True`, the image is resized to a size that is a multiple of this value keep_aspect_ratio (`bool`, *optional*, defaults to `False`): If `True`, and `do_resize` is `True`, the image is resized to the largest possible size such that the aspect ratio is preserved. Returns: `torch.Tensor`: The resized image. zDThe size dictionary must contain the keys 'height' and 'width'. Got )rrr)r:r;)r*r+ ValueErrorkeysr6rresize)selfr8r9r:r;r<rrr%r%r&r?hs   zDPTImageProcessorFast.resize size_divisorc CsN|jdd\}}dd}|||\}}|||\}} ||| |f} t|| S)a Center pad a batch of images to be a multiple of `size_divisor`. Args: image (`torch.Tensor`): Image to pad. Can be a batch of images of dimensions (N, C, H, W) or a single image of dimensions (C, H, W). size_divisor (`int`): The width and height of the image will be padded to a multiple of this number. r(NcSs2t|||}||}|d}||}||fS)Nr)rr )r9rAnew_sizepad_size pad_size_leftpad_size_rightr%r%r&_get_pads z1DPTImageProcessorFast.pad_image.._get_pad)r,tvFpad) r@r8rAr*r+rFpad_top pad_bottompad_left pad_rightpaddingr%r%r& pad_images   zDPTImageProcessorFast.pad_imageimagesdo_reduce_labels do_resizedo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_paddisable_groupingreturn_tensorsc Ks|r||}t||d\}}i}|D]\}}|r%|j||||| d}|||<qt||}t||d\}}i}|D]"\}}|rI|||}|rQ|||}|||| | | | }|||<q=t||}td|i|dS)N)rZ)r8r9r:r<r pixel_values)data tensor_type) reduce_labelritemsr?r center_croprNrescale_and_normalizer)r@rOrPrQr9r:rRrSrTrUrVrWrXrr<rYrArZr[kwargsgrouped_imagesgrouped_images_indexresized_images_groupedr,stacked_imagesresized_imagesprocessed_images_groupedprocessed_imagesr%r%r& _preprocesss8        z!DPTImageProcessorFast._preprocessoutputsr target_sizescCst|d|j}|durt|t|krtdg}|dur%dgt|n|}t||D]"\}}|durGtjjj| d d|ddd }| d |iq,|S) a Converts the raw output of [`DepthEstimatorOutput`] into final depth predictions and depth PIL images. Only supports PyTorch. Args: outputs ([`DepthEstimatorOutput`]): Raw outputs of the model. target_sizes (`TensorType` or `List[Tuple[int, int]]`, *optional*): Tensor of shape `(batch_size, 2)` or list of tuples (`Tuple[int, int]`) containing the target size (height, width) of each image in the batch. If left to None, predictions will not be resized. Returns: `List[Dict[str, TensorType]]`: A list of dictionaries of tensors representing the processed depth predictions. torchNz]Make sure that you pass in as many target sizes as the batch dimension of the predicted depthrrbicubicF)r9mode align_cornerspredicted_depth) rrrlenr=ziprnnn functional interpolate unsqueezesqueezeappend)r@rlrmrrresultsdepth target_sizer%r%r&post_process_depth_estimations" z3DPTImageProcessorFast.post_process_depth_estimation)NTrF)rr)&__name__ __module__ __qualname__r BICUBICresampler rWr rXr9rQrTrVrYrUr<rrSrRrPr valid_kwargsr rboolintr?rNlistfloatstrrrrktupledictr~r%r%r%r&r7Us  -        =r7)'rcollections.abcrtypingrrrnimage_processing_baserimage_processing_utils_fastrimage_transformsrr image_utilsr r r r utilsrrrbeit.image_processing_beit_fastrimage_processing_dptrmodeling_outputsr$torchvision.transforms.v2.functional transformsv2rvrGrrr6r7__all__r%r%r%r&s:        ' =