Skip to content

Latest commit

 

History

History
28 lines (22 loc) · 709 Bytes

DATA.md

File metadata and controls

28 lines (22 loc) · 709 Bytes
Raw

Data Preparation

Please download KITTI dataset and organize the data as follows:

#MonoDTR_ROOT
  |data/
    |KITTI/
      |object/			
        |training/
          |calib/
          |image_2/
          |label_2/
          |velodyne/
        |testing/
          |calib/
          |image_2/

You can modify the path in config/config.py (for train / val split), and then run the preparation script:

cd #MonoDTR_ROOT
./launchers/det_precompute.sh config/config.py train # precompute image database and anchors mean/std
python scripts/depth_gt_compute.py --config=config/config.py # precompute depth gt for training