Pointpillars 环境部署 ubuntu18.04

源码链接https://gitee.com/luogyu/liu-qingzhen_nutonomy_pointpillars

原码(https://github.com/nutonomy/second.pytorch) 中缺少 nms.so 文件  ，不过此类问题可以通过 该问题解决方式解决，但我没有继续尝试。链接地址：https://github.com/traveller59/second.pytorch/issues/69

步骤1， git clone 命令下载到本地目录 。

按照ReadMe 文件执行 环境配置操作。

依次是

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

pip install --upgrade pip
pip install fire tensorboardX

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

Add second.pytorch/ to your PYTHONPATH.

. 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"
}

这里是自己已经编辑好的 .proto目录

训练：

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

评估： 

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

OVER：

FINE.