A tensorflow implementation for VoxelNet.

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

0. have a look at config.py for model configurations, split your data into test/train set by this.
1. run setup.py to build the Cython module.

$ python setup.py build_ext --inplace

2. 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  

3. run train.py. Some cmdline parameters is needed, just check train.py for them.
4. launch a tensorboard and wait for the training result.

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

TBD

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

MIT