Build a dataset, defined by `dataset_name`. Args: cfg (eDICT): Returns: Dataset: a constructed dataset specified by data

Disable the redundant torch default initialization to accelerate model creation.

Source: https://github.com/facebookresearch/pytorch3d/blob/main/pytorch3d/transforms/rotation_conversions.py Apply the rotation given by a

Calculate Euclid distance between each two points. src^T * dst = xn * xm + yn * ym + zn * zm； sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;

Computes the accuracy over the k top predictions for the specified values of k

Input: xyz: pointcloud data, [B, N, 3] npoint: number of samples Return: centroids: sampled pointcloud index, [B, npo

data B N 3 number int

data B N 3 number int

data B N 3 number int

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding c

Args: results: dict or file path to the json file containing the dict output_file: the path the final evaluation results to be sa

Helper that gets a list of the model's attention modules. Each module has a `bias` buffer used for causal masking. The Prefix LM conv

Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of para

Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of para

Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Retur

Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Retur