Get sorted list of class names. Args: gt: Returns: Sorted list of class names.

Args: point_centers: (N, 3) max_neighbour_distance: float num_voxels: [num_x, num_y, num_z] Retu

Loads depth map for a sample Args: idx: str, Sample index Returns: depth: (H, W), Depth map

Compute the precision envelope. Args: precisions: Returns:

Loads image for a sample Args: idx: int, Sample index Returns: image: (H, W, 3), RGB Image

Generate the dataset infos dict for each sample of the dataset. For each sample, this dict contains: - the sequence index

Return two lists, one for the model parameters in FP16 and one for the master parameters in FP32.

Args: rois: (N, 7) roi_labels: (N) gt_boxes: (N, ) gt_labels: Returns:

Get model Args: constructor: function, Model constructor Returns: model: nn.Module, Model

Returns the data path as well as all annotations related to that sample_data. Note that the boxes are transformed into the current sensor's c

Args: batch_dict: Returns: keypoints: (N1 + N2 + ..., 4), where 4 indicates [bs_idx, x, y, z]

Calculate grid to LiDAR unprojection for each plane Args: pc_min: [x_min, y_min, z_min], Minimum of point cloud range (m)

:param u: (N) :param v: (N) :param depth_rect: (N) :return:

Args: keypoints: (N1 + N2 + ..., 4) bev_features: (B, C, H, W) batch_size: bev_stride:

Compute pairwise intersection areas between boxes. Args: boxes1: a numpy array with shape [N, 4] holding N boxes boxes2: a numpy

Computes pairwise intersection-over-union between box collections. Args: boxes1: a numpy array with shape [N, 4] holding N boxes.

:param pts_lidar: (N, 3) :return pts_img: (N, 2)

Loads from binary format. Data is stored as (x, y, z, intensity, ring index). :param file_name: <str>. :return: <np.float: 4,