Skip to content
Projects

tsinghua-rll/VoxelNet-tensorflow

View on GitHub

tsinghua-rll/VoxelNet-tensorflow has 469 GitHub stars and 118 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-21 06:15 UTC. Last push 2019-08-15.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
Collecting history
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

A 3D object detection system for autonomous driving.

Machine Learning

README.md

Original

VoxelNet-tensorflow

A tensorflow implementation for VoxelNet.

Requirement

  1. Python 3.5+
  2. tensorflow 1.4+
  3. NumPy, etc.

Usage

  1. have a look at config.py for model configurations, split your data into test/train set by this.
  2. run setup.py to build the Cython module.
$ python setup.py build_ext --inplace
  1. make sure your working directory looks like this (some files are omitted):
├── build   <-- Cython build file
├── model   <-- some src files
├── utils   <-- some src files
├── setup.py   
├── config.py   
├── test.py   
├── train.py   
├── train_hook.py   
├── README.md    
└── data    <-- KITTI data directory 
    └── object 
        ├── training   <-- training data
        |   ├── image_2   
        |   ├── label_2   
        |   └── velodyne  
        └── testing  <--- testing data
            ├── image_2   
            ├── label_2   
            └── velodyne  
  1. run train.py. Some cmdline parameters is needed, just check train.py for them.
  2. launch a tensorboard and wait for the training result.

Data augmentation

Since c928317, data augmentation is done in an online manner, so there is no need for generating augmented samples.

Result

TBD

Acknowledgement

Thanks to @ring00 for the implementation of VFE layer and Jialin Zhao for the implementation of the RPN.

License

MIT