voxelnext_3d_box/config.yaml

SAM_TYPE: "vit_h"
SAM_CHECKPOINT: "sam_vit_h_4b8939.pth"

POINT_CLOUD_RANGE: [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
USED_FEATURE_LIST: ['x', 'y', 'z', 'intensity', 'timestamp']
DATA_PROCESSOR:
    - NAME: mask_points_and_boxes_outside_range
      REMOVE_OUTSIDE_BOXES: True

    - NAME: shuffle_points
      SHUFFLE_ENABLED: {
        'train': True,
        'test': True
      }

    - NAME: transform_points_to_voxels
      VOXEL_SIZE: [0.075, 0.075, 0.2]
      MAX_POINTS_PER_VOXEL: 10
      MAX_NUMBER_OF_VOXELS: {
        'train': 120000,
        'test': 160000
      }

VOXELNEXT_CHECKPOINT: "voxelnext_nuscenes_kernel1.pth"
INPUT_CHANNELS: 5
GRID_SIZE: [1440, 1440, 40]

CLASS_NAMES: ['car','truck', 'construction_vehicle', 'bus', 'trailer',
  'barrier', 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone']

KERNEL_SIZE_HEAD: 1

VOXEL_SIZE: [0.075, 0.075, 0.2]
CLASS_NAMES_EACH_HEAD: [
  ['car'],
  ['truck', 'construction_vehicle'],
  ['bus', 'trailer'],
  ['barrier'],
  ['motorcycle', 'bicycle'],
  ['pedestrian', 'traffic_cone'],
]

SEPARATE_HEAD_CFG:
    HEAD_ORDER: ['center', 'center_z', 'dim', 'rot', 'vel']
    HEAD_DICT: {
        'center': {'out_channels': 2, 'num_conv': 2},
        'center_z': {'out_channels': 1, 'num_conv': 2},
        'dim': {'out_channels': 3, 'num_conv': 2},
        'rot': {'out_channels': 2, 'num_conv': 2},
        'vel': {'out_channels': 2, 'num_conv': 2},
    }

POST_PROCESSING:
    SCORE_THRESH: 0
    POST_CENTER_LIMIT_RANGE: [-61.2, -61.2, -10.0, 61.2, 61.2, 10.0]
    MAX_OBJ_PER_SAMPLE: 500