process_file. Args: filepath: path to the main file mode: typically train, test or validation Returns:

Ravel the coordinates after subtracting the min coordinates.

Read txt file into lines.

Read txt file into lines.

Read txt file into lines.

Read txt file into lines.

Makes a function retry itself after encountering pytorch's CUDA OOM error. It will first retry after calling `torch.cuda.empty_cache()`.

Evaluate the given model. The given model is expected to already contain weights to evaluate. Args: cfg (CfgNode)

Convert the model into training mode while keep layers freezed.

Inputs: intrinsics: B X V X 3 X 3 poses: B X V X 4 X 4 (torch.tensor) depths: B X V X H X W (torch.tensor) Outpu

visualize PCA of features Keyword arguments: feature_folders -- list of feature folders Return: None

Input: voxel_map (B, N1, C) point2voxel (B, N) Output: src_new (B, N, C)

Input: voxel_map (B, N1, C) point2voxel (B, N) Output: src_new (B, N, C)

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

------------------------------------API------------------------------------------

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Args: dataset_dict (dict): Metadata of one video Returns: dict: a format that builtin models in ...

Args: backbone: a backbone module, must follow detectron2's backbone interface sem_seg_head: a module that predicts s

Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category ma

NOTE: this interface is experimental. Args: in_channels: channels of the input features mask_classification:

Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels. stride

Args: bottleneck_channels (int): number of output channels for the 3x3 "bottleneck" conv layers. num_

Args: norm (str or callable): norm after the first conv layer. See :func:`layers.get_norm` for supported format.

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features n

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features t

Multi-Scale Deformable Attention Module :param d_model hidden dimension :param n_levels number of feature levels

NOTE: this interface is experimental. Args: is_train: for training or inference augmentations: a list of augm

Args: sampler (Sampler): Base sampler. group_ids (list[int]): If the sampler produces indices in range [0, N),

Args: dataset: an old-style dataset with ``__getitem__`` sampler: a cheap iterable that produces indices to be applie

Args: size (int): the total number of data of the underlying dataset to sample from shuffle (bool): whether to shuffl

Args: dataset_name (str): name of the dataset to be evaluated. It must have either the following corresponding me

Constructor of Microsoft COCO helper class for reading and visualizing annotations. :param annotation_file (str): location of annotat

Initialize CocoEval using coco APIs for gt and dt :param cocoGt: coco object with ground truth annotations :param cocoDt: coc