How to split the data ?

[cuge1995]

the original . ├── testing │   ├── calib │   ├── det_2 │   ├── image_2 │   ├── image_3 │   ├── prev_2 │   ├── prev_3 │   └── velodyne └── training ├── calib ├── det_2 ├── image_2 ├── image_3 ├── label_2 ├── prev_2 ├── prev_3 └── velodyne

[WeijingShi]

Can you elaborate on your question?

[cuge1995]

the dataset I download from KITTI and unzip it, the tree structure of the file is as above.

[WeijingShi]

By default, we recommend the following file structure. For the details, please refer to README

DATASET_ROOT_DIR
├── image                    #  Left color images
│   ├── training
|   |   └── image_2            
│   └── testing
|       └── image_2 
├── velodyne                 # Velodyne point cloud files
│   ├── training
|   |   └── velodyne            
│   └── testing
|       └── velodyne 
├── calib                    # Calibration files
│   ├── training
|   |   └──calib            
│   └── testing
|       └── calib 
├── labels                   # Training labels
│   └── training
|       └── label_2
└── 3DOP_splits              # split files.
    ├── train.txt
    ├── train_car.txt
    └── ...