Can I use this model on Argoverse dataset in kitti format?

[BBBeatrice]

Hi, @hailanyi ,thanks for your great work! I am trying to use this multimodal model on Argoverse dataset, since it is now working well with kitti, I use this work https://github.com/cxy1997/3D_adapt_auto_driving to change data of argoverse into kitti format. Although the data format has been the same, the result of the model is still strange, all the output is 0.0. I searched some solution but there is no exactly same problem as I met. Also, I tried to modify kitti_dataset.yaml to make the dataset fit the model, but there is no obvious improvement now. Here is the kitti_dataset.yaml.(I changed POINT_CLOUD_RANGE to solve the error when running)

Hope you can give me some advice!

  ```
  DATA_PATH: '../data/kitti'
  DATASET: 'KittiDataset'

  MM_PATH: 'velodyne_depth'
  POINT_CLOUD_RANGE: [0, -40, -1.0, 70.4, 40, 3.0]

  DATA_SPLIT: {
      'train': train,
      'test': val
  }

  INFO_PATH: {
      'train': [kitti_infos_train.pkl],
      'test': [kitti_infos_val.pkl],
  }

  FOV_POINTS_ONLY: True

  DATA_AUGMENTOR:
      DISABLE_AUG_LIST: ['placeholder']
      AUG_CONFIG_LIST:
          - NAME: gt_sampling
            USE_ROAD_PLANE: True
            DB_INFO_PATH:
                - kitti_dbinfos_train.pkl
            PREPARE: {
               filter_by_min_points: ['Car:5', 'Pedestrian:5', 'Cyclist:5'],
               filter_by_difficulty: [-1],
            }

            SAMPLE_GROUPS: ['Car:15','Pedestrian:10', 'Cyclist:10']
            NUM_POINT_FEATURES: 4
            DATABASE_WITH_FAKELIDAR: False
            REMOVE_EXTRA_WIDTH: [0.0, 0.0, 0.0]
            LIMIT_WHOLE_SCENE: False

          - NAME: random_world_flip
            ALONG_AXIS_LIST: ['x']

          - NAME: random_world_rotation
            WORLD_ROT_ANGLE: [-0.78539816, 0.78539816]

          - NAME: random_world_scaling
            WORLD_SCALE_RANGE: [0.95, 1.05]

  POINT_FEATURE_ENCODING:` {
      encoding_type: absolute_coordinates_encoding,
      used_feature_list: ['x', 'y', 'z', 'intensity'],
      src_feature_list: ['x', 'y', 'z', 'intensity'],

  }

  DATA_PROCESSOR:
      - NAME: mask_points_and_boxes_outside_range
        REMOVE_OUTSIDE_BOXES: True

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

      - NAME: transform_points_to_voxels
        VOXEL_SIZE: [0.05, 0.05, 0.1]
        MAX_POINTS_PER_VOXEL: 5

        MAX_NUMBER_OF_VOXELS: {
          'train': 160000,
          'test': 400000
        }