Welcome to PointPillars.

This repo demonstrates how to reproduce the results from PointPillars: Fast Encoders for Object Detection from Point Clouds (to be published at CVPR 2019) on the KITTI dataset by making the minimum required changes from the preexisting open source codebase SECOND.

This is not an official nuTonomy codebase, but it can be used to match the published PointPillars results.

This is a fork of SECOND for KITTI object detection and the relevant subset of the original README is reproduced here.

ONLY supports python 3.6+, pytorch 0.4.1+. Code has only been tested on Ubuntu 16.04/18.04.

git clone https://github.com/nutonomy/second.pytorch.git

It is recommend to use the Anaconda package manager.

First, use Anaconda to configure as many packages as possible.

conda create -n pointpillars python=3.7 anaconda
source activate pointpillars
conda install shapely pybind11 protobuf scikit-image numba pillow
conda install pytorch torchvision -c pytorch
conda install google-sparsehash -c bioconda

Then use pip for the packages missing from Anaconda.

pip install --upgrade pip
pip install fire tensorboardX

Finally, install SparseConvNet. This is not required for PointPillars, but the general SECOND code base expects this to be correctly configured.

git clone git@github.com:facebookresearch/SparseConvNet.git
cd SparseConvNet/
bash build.sh
# NOTE: if bash build.sh fails, try bash develop.sh instead

Additionally, you may need to install Boost geometry:

sudo apt-get install libboost-all-dev

You need to add following environment variables for numba to ~/.bashrc:

export NUMBAPRO_CUDA_DRIVER=/usr/lib/x86_64-linux-gnu/libcuda.so
export NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so
export NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice

Add second.pytorch/ to your PYTHONPATH.

Download KITTI dataset and create some directories first:

└── KITTI_DATASET_ROOT
       ├── training    <-- 7481 train data
       |   ├── image_2 <-- for visualization
       |   ├── calib
       |   ├── label_2
       |   ├── velodyne
       |   └── velodyne_reduced <-- empty directory
       └── testing     <-- 7580 test data
           ├── image_2 <-- for visualization
           ├── calib
           ├── velodyne
           └── velodyne_reduced <-- empty directory

Note: PointPillar's protos use KITTI_DATASET_ROOT=/data/sets/kitti_second/.

python create_data.py create_kitti_info_file --data_path=KITTI_DATASET_ROOT

python create_data.py create_reduced_point_cloud --data_path=KITTI_DATASET_ROOT

python create_data.py create_groundtruth_database --data_path=KITTI_DATASET_ROOT

The config file needs to be edited to point to the above datasets:

train_input_reader: {
  ...
  database_sampler {
    database_info_path: "/path/to/kitti_dbinfos_train.pkl"
    ...
  }
  kitti_info_path: "/path/to/kitti_infos_train.pkl"
  kitti_root_path: "KITTI_DATASET_ROOT"
}
...
eval_input_reader: {
  ...
  kitti_info_path: "/path/to/kitti_infos_val.pkl"
  kitti_root_path: "KITTI_DATASET_ROOT"
}

cd ~/second.pytorch/second
python ./pytorch/train.py train --config_path=./configs/pointpillars/car/xyres_16.proto --model_dir=/path/to/model_dir

• If you want to train a new model, make sure "/path/to/model_dir" doesn't exist.
• If "/path/to/model_dir" does exist, training will be resumed from the last checkpoint.
• Training only supports a single GPU.
• Training uses a batchsize=2 which should fit in memory on most standard GPUs.
• On a single 1080Ti, training xyres_16 requires approximately 20 hours for 160 epochs.

cd ~/second.pytorch/second/
python pytorch/train.py evaluate --config_path= configs/pointpillars/car/xyres_16.proto --model_dir=/path/to/model_dir

• Detection result will saved in model_dir/eval_results/step_xxx.
• By default, results are stored as a result.pkl file. To save as official KITTI label format use --pickle_result=False.