LiDAR2camera_self_check

Table of Contents

• Requirements
• Evaluation
• Train
• Citation

Requirements

• python 3.6 (recommend to use Anaconda)
• PyTorch==1.0.1.post2
• Torchvision==0.2.2
• Install requirements and dependencies

pip install -r requirements.txt

Evaluation

1. Download KITTI odometry dataset.
2. Change the path to the dataset in evaluate_calib.py.

data_folder = '/path/to/the/KITTI/odometry_color/'

3. Create a folder named pretrained to store the pre-trained models in the root path.
4. Download pre-trained models and modify the weights path in evaluate_calib.py.

weights = [
    # './pretrained/final_checkpoint_r20.00_t1.50_e4_0.094.tar',
    # './pretrained/final_checkpoint_r2.00_t0.20_e4_0.228.tar',
    # './pretrained/final_checkpoint_r10.00_t1.00_e3_0.108.tar',
    './pretrained/final_checkpoint_r5.00_t0.50_e-1_0.145.tar',
]

5. Run evaluation.

python evaluate_calib.py

Train

python train_with_sacred.py

Acknowledgments

We are grateful to Daniele Cattaneo for his CMRNet github repository and LCCNet github repository. We use them as our initial code base.

---