Convert keys in checkpoints for VoteNet. There can be some breaking changes during the development of mmdetection3d, and this tool is used fo

Converts MMDetection3D model (config + checkpoint) to TorchServe `.mar`. Args: config_file (str): In MMDetection3D config for

Calculate naive dice loss, the coefficient in the denominator is the first power instead of the second power. Args: pred (torch.Tenso

Convert points to range (0, 1). Args: line (LineString): line Returns: normalized (array): normalized point

Serialize picklable python object to tensor.

Obtain history BEV features iteratively. To save GPU memory, gradients are not calculated.

r""" Parameters ---------- path : str Returns ------- list

Parse config from strings. Args: config_strings (string): strings of model config. Returns: Config: model config

Parse config from strings. Args: config_strings (string): strings of model config. Returns: Config: model config

Parse config from strings. Args: config_strings (string): strings of model config. Returns: Config: model config

Produces a colored string for printing Parameters ---------- string : str String that will be colored color : str

r""" Parameters ---------- path : str obj : object

format the predictions find the mask

Get the intersection of the convex hull of the reprojected bbox corners and the image canvas, return None if no intersection. Args: c

Get the intersection of the convex hull of the reprojected bbox corners and the image canvas, return None if no intersection. Args: c

Training data preparation. Args: index (int): Index for accessing the target data. Returns: dict: Tra

Randomly sample an img_scale when ``ratio_range`` is specified. A ratio will be randomly sampled from the range specified by ``ratio_

Random sampling. Sampling point cloud to a certain number of points. Args: points (ndarray): Point cloud. num_points (int):

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns