1. Introduction
2. Environment
3. Datasets
4. Run
5. Frameworks
6. Citation
7. Acknowledgement
   
   

This repository provides a benchmark tool for well-known deep learning-based 3D detectors on NVIDIA Jeston boards. Currently, we provide benchmarks of 12 detectors (Check (#Frameworks)!). We have tested the tool on the four Jetson series including AGX, NX, TX2, and Nano.

The work analyzes frame per second (FPS) and resource usages (CPU, GPU, RAM, Power consumption) of each detector on the Jetsons.

1. git clone "this repository" 
2. sudo pip install -r requirements.txt

1. cd weights/
2. bash download_weights.sh

• Jetpack 4.4.1
• CUDA Toolkit 10.2
• Python 3.6.9
• Please check "requirements.txt" for the detailed libraries.
• The best configuration of each framework can be found in cfg folder.

We run the benchmak using two datasets: KITTI and nuScenes. You can download the datasets from below links.

Make sure that place the datasets in 'datasets' folder.

• datasets/KITTI/*
• datasets/nuScenes/*

Run 'resource_anlyzer.py' in 'src/resource_analyzer' folder. You need to specify the "--model" and "--output".

$  python resource_analyzer.py --model Complex-YOLOv4 --output/C-YOLOv4  

Thanks for the contributors on 3D detectors. Please move to each branch for detailed instructions about source codes.

Not yet available..

@article{Soon...
}

Not yet available..