assign a 0/1 label to each voxel based on whether the center of voxel is in gt_box. LIDAR.

box decode for VoxelNet in lidar Args: boxes ([N, 7] Tensor): normal boxes: x, y, z, w, l, h, r anchors ([N, 7] Tensor): anchor

box decode for VoxelNet in lidar Args: boxes ([N, 7] Tensor): normal boxes: x, y, z, w, l, h, r anchors ([N, 7] Tensor): anchors

box encode for VoxelNet in lidar Args: boxes ([N, 7] Tensor): normal boxes: x, y, z, w, l, h, r anchors ([N, 7] Tensor): anchor

box encode for VoxelNet Args: boxes ([N, 7] Tensor): normal boxes: x, y, z, l, w, h, r anchors ([N, 7] Tensor): anchors

Build losses based on the config. Builds classification, localization losses and optionally a hard example miner based on the config. Args:

Create optimizer based on config. Args: optimizer_config: A Optimizer proto message. Returns: An optimizer and a list of var

build second pytorch instance.

Create lr scheduler based on config. note that lr_scheduler must accept a optimizer that has been restored. Args: optimizer_config: A Optimiz

Create optimizer based on config. Args: optimizer_config: A Optimizer proto message. Returns: An optimizer and a list of variables for s

Builds a tensor dictionary based on the InputReader config. Args: input_reader_config: A input_reader_pb2.InputReader object. Return

Create optimizer based on config. Args: optimizer_config: A Optimizer proto message. Returns: An optimizer and a list of variables for s

Builds a tensor dictionary based on the InputReader config. Args: input_reader_config: A input_reader_pb2.InputReader object. Return

Builds a tensor dictionary based on the InputReader config. Args: input_reader_config: A input_reader_pb2.InputReader object. Return

Create optimizer based on config. Args: optimizer_config: A Optimizer proto message. Returns: An optimizer and a list of var

Builds a tensor dictionary based on the InputReader config. Args: input_reader_config: A input_reader_pb2.InputReader object. Return

Builds a classification loss for Faster RCNN based on the loss config. Args: loss_config: A losses_pb2.ClassificationLoss object. Returns:

convert kitti locations, dimensions and angles to corners Args: centers (float array, shape=[N, 2]): locations in kitti label file.

convert kitti locations, dimensions and angles to corners Args: centers (float array, shape=[N, 3]): locations in kitti label file.

generate relative 2d box corners based on length per dim and origin point. Args: dims (float array, shape=[N, 2]): array of lengt

Args: feature_size: list [D, H, W](zyx) sizes: [N, 3] list of list or array, size of anchors, xyz Returns: anc

Args: feature_size: list [D, H, W](zyx) sizes: [N, 3] list of list or array, size of anchors, xyz Returns: anc