a hG0@s,ddlZddlmZddlmZmZmZddlmZddl m Z m Z ddl m Z mZddlmZmZmZmZdd lmZmZmZmZmZmZd d lmZerdd lmZerddlZerdd l m!Z"nerdd l#m!Z"dee$ee$fe%e$edddZ&Gddde Z'eGdddeZ(dgZ)dS)N)Iterable) TYPE_CHECKINGOptionalUnion) BatchFeature)BaseImageProcessorFastDefaultFastImageProcessorKwargs)group_images_by_shapereorder_images)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDPILImageResamplingSizeDict) TensorTypeauto_docstringis_torch_availableis_torchvision_availableis_torchvision_v2_availablerequires_backends)BeitImageProcessorFast)DepthEstimatorOutput) functional torch.Tensor) input_image output_sizekeep_aspect_ratiomultiplereturnc Csddd}|jdd\}}|\}}||} ||} |rZtd| td| krV| } n| } || ||d} || ||d} t| | dS) NrcSsPt|||}|dur2||kr2t|||}||krLt|||}|S)N)roundmathfloorceil)valrZmin_valZmax_valxr&_/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/dpt/modular_dpt.pyconstrain_to_multiple_of;s z>get_resize_output_image_size..constrain_to_multiple_of)rheightwidth)rN)shapeabsr) rrrrr(Z input_heightZ input_widthZ output_heightZ output_widthZ scale_heightZ scale_widthZ new_heightZ new_widthr&r&r'get_resize_output_image_size5s r0c@sNeZdZUdZeeed<eeed<eeed<eeed<eeed<dS)DPTFastImageProcessorKwargsa ensure_multiple_of (`int`, *optional*, defaults to 1): If `do_resize` is `True`, the image is resized to a size that is a multiple of this value. Can be overidden by `ensure_multiple_of` in `preprocess`. do_pad (`bool`, *optional*, defaults to `False`): Whether to apply center padding. This was introduced in the DINOv2 paper, which uses the model in combination with DPT. size_divisor (`int`, *optional*): If `do_pad` is `True`, pads the image dimensions to be divisible by this value. This was introduced in the DINOv2 paper, which uses the model in combination with DPT. keep_aspect_ratio (`bool`, *optional*, defaults to `False`): If `True`, the image is resized to the largest possible size such that the aspect ratio is preserved. Can be overidden by `keep_aspect_ratio` in `preprocess`. 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. ensure_multiple_of size_divisordo_padrdo_reduce_labelsN)__name__ __module__ __qualname____doc__rint__annotations__boolr&r&r&r'r1\s     r1c@s4eZdZejZeZeZ dddZ dZ dZ dZ dZdZdZdZdZdZdZdZeZdded eeeedd d d Zddedd ddZedeeeed eeeeeeeeeefeeeeefeeeeeeeeeee e!fe"dddZ#ddeee!ee$eefdfee%e e!fdddZ&dS)DPTImageProcessorFastir+TFgp?r*NrzF.InterpolationMode)imagesize interpolation antialiasr2rrcCsJ|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@rA)r,r- ValueErrorkeysr0rresize)selfr>r?r@rAr2rrr&r&r'rDs   zDPTImageProcessorFast.resize)r>r3rc 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)r!r#)r?r3new_sizeZpad_sizeZ pad_size_leftZpad_size_rightr&r&r'_get_pads z1DPTImageProcessorFast.pad_image.._get_pad)r.Fpad) rEr>r3r,r-rGpad_topZ pad_bottompad_left pad_rightpaddingr&r&r' pad_images  zDPTImageProcessorFast.pad_image)imagesr5 do_resizer?r@do_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stdrr2r4r3disable_groupingreturn_tensorsrc Ks|r||}t||d\}}i}|D](\}}|rJ|j||||| d}|||<q*t||}t||d\}}i}|D]D\}}|r|||}|r|||}|||| | | | }|||<qzt||}|rtj |ddn|}t d|idS)N)rX)r>r?r@r2rr)dimZ pixel_values)data) Z reduce_labelr itemsrDr Z center_croprNZrescale_and_normalizetorchstackr)rErOr5rPr?r@rQrRrSrTrUrVrWrr2r4r3rXrYkwargsZgrouped_imagesZgrouped_images_indexZresized_images_groupedr.Zstacked_imagesZresized_imagesZprocessed_images_groupedZprocessed_imagesr&r&r' _preprocesss:        z!DPTImageProcessorFast._preprocessr)outputs target_sizesrcCst|d|j}|dur0t|t|kr0tdg}|durJdgt|n|}t||D]D\}}|durtjjj| d d|ddd }| d |iqX|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. r]Nz]Make sure that you pass in as many target sizes as the batch dimension of the predicted depthrr*ZbicubicF)r?modeZ align_cornerspredicted_depth) rrdlenrBzipr]nnrZ interpolateZ unsqueezeZsqueezeappend)rErarbrdresultsdepthZ target_sizer&r&r'post_process_depth_estimation s  z3DPTImageProcessorFast.post_process_depth_estimation)NTr*F)r*)N)'r6r7r8rZBICUBICZresampler rVr rWr?rPrSrUr4rTr2rr5rRrQr1Z valid_kwargsrr<rr:rDrNlistfloatrstrrrr`tupledictrkr&r&r&r'r=wsz  -  >r=)*r!collections.abcrtypingrrrZimage_processing_baserZimage_processing_utils_fastrr Zimage_transformsr r Z image_utilsr r rrutilsrrrrrrZbeit.image_processing_beit_fastrZmodeling_outputsrr]Ztorchvision.transforms.v2rrHZtorchvision.transformsr:r<r0r1r=__all__r&r&r&r's6       '?