A tensorflow inplementation for VoxelNet.
- have a look at
config.py
for model configurations, and make sure that you are usingPython3.5+
. - run
setup.py
to build the Cython module.
$ python setup.py build_ext --inplace
- run
train.py
. Some cmdline parameters is needed, just checktrain.py
for them. - 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
- nan and inf bugs fix
- multicard support
- data augmentation
Thanks to @ring00 for the implementation of VFE layer and Jialin Zhao for the implementation of the RPN.