Skip to content

Latest commit

 

History

History
162 lines (115 loc) · 4.03 KB

TRAIN.md

File metadata and controls

162 lines (115 loc) · 4.03 KB

Training and evaluating the pointpillars to get suitable weights

|On GeForce 2070Ti|

Based on nutonomy/second.pytorch

Getting Started

Install

1. Clone code

git clone https://github.com/hova88/Lidardet.git

2. Install Python packages

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

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

git clone [email protected]: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

3. Setup cuda for numba

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

Useing nutonomy/second.pytorch Repo to Prepare dataset

0.clone nutonomy/second.pytorch

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

Add Lidardet/ to your PYTHONPATH.

export PYTHONPATH=path/to/Lidardet/second.pytorch

1. Dataset preparation

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/.

2. Create kitti infos:

python create_data.py create_kitti_info_file --data_path=KITTI_DATASET_ROOT

3. Create reduced point cloud:

python create_data.py create_reduced_point_cloud --data_path=KITTI_DATASET_ROOT

4. Create groundtruth-database infos:

python create_data.py create_groundtruth_database --data_path=KITTI_DATASET_ROOT

5. Modify config file

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"
}

Train

cd Path/to/Lidardet/

export PYTHONPATH=path/to/Lidardet

python ./train.py train --config_path=./params/configs/pointpillars_kitti_car_xy16.yaml --model_dir=/path/to/logs/XXX
  • 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 2070Ti, training xyres_16 requires approximately 30 hours for 1000 epochs.

Evaluate

  • 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.