Skip to content

The PyTorch Implementation of F-ConvNet for 3D Object Detection

License

Notifications You must be signed in to change notification settings

Gorilla-Lab-SCUT/frustum-convnet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

This repository is the code for our IROS 2019 paper [arXiv],[IEEEXplore].

Citation

If you find this work useful in your research, please consider citing.

@inproceedings{wang2019frustum,
    title={Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection},
    author={Wang, Zhixin and Jia, Kui},
    booktitle={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
    pages={1742--1749},
    year={2019},
    organization={IEEE}
}

Installation

Requirements

  • PyTorch 1.0+
  • Python 3.6+

We test our code under Ubuntu-16.04 with CUDA-9.0, CUDNN-7.0, Python-3.7.2, PyTorch-1.0.

Clone the repository and install dependencies

git clone https://github.com/zhixinwang/frustum-convnet.git

You may need to install extra packages, like pybind11, opencv, yaml, tensorflow(optional).

If you want to use tensorboard to visualize the training status, you should install tensorflow (CPU version is enough). Otherwise, you should set the config 'USE_TFBOARD: False' in cfgs/*.yaml.

Compile extension

cd ops
bash clean.sh
bash make.sh

Download data

Download the KITTI 3D object detection dataset from here and organize them as follows.

data/kitti
├── testing
│   ├── calib
│   ├── image_2
│   └── velodyne
└── training
    ├── calib
    ├── image_2
    ├── label_2
    └── velodyne

Training and evaluation

First stage

Run following command to prepare pickle files for car training. We use the 2D detection results from F-PointNets. The pickle files will be saved in kitti/data/pickle_data.

python kitti/prepare_data.py --car_only --gen_train --gen_val --gen_val_rgb_detection

Run following commands to train and evaluate the final model. You can use export CUDA_VISIBLE_DEVICES=? to specify which GPU to use. And you can modify the setting after OUTPUT_DIR to set a directory to save the log, model files and evaluation results. All the config settings are under the configs/config.py.

python train/train_net_det.py --cfg cfgs/det_sample.yaml OUTPUT_DIR output/car_train
python train/test_net_det.py --cfg cfgs/det_sample.yaml OUTPUT_DIR output/car_train TEST.WEIGHTS output/car_train/model_0050.pth

We also provide the shell script, so you can also run bash scripts/car_train.sh instead.

Refinement stage

Run following command to prepare pickle files for car training. We use the first stage predicted results. If you don't use the default directory in the first stage, you should change the corresponding directory in here and here before running following commands. The pickle files will be saved in kitti/data/pickle_data_refine.

python kitti/prepare_data_refine.py --car_only --gen_train --gen_val_det --gen_val_rgb_detection

Run following commands to train and evaluate the final model.

python train/train_net_det.py --cfg cfgs/refine_car.yaml OUTPUT_DIR output/car_train_refine
python train/test_net_det.py --cfg cfgs/refine_car.yaml OUTPUT_DIR output/car_train_refine TEST.WEIGHTS output/car_train_refine/model_0050.pth

We also provide the shell script, so you can also run bash scripts/car_train_refine.sh instead.

All commands in one script file

You can simply run bash scripts/car_all.sh to execute all the above commands.

Pretrained models

We provide the pretrained models for car category, you can download from here. After extracting the files under root directory, you can run bash scripts/eval_pretrained_models.sh to evaluate the pretrained models. The performance on validation set is as follows:

# first stage
Car AP@0.70, 0.70, 0.70:
bbox AP:98.33, 90.40, 88.24
bev  AP:90.32, 88.02, 79.41
3d   AP:87.76, 77.41, 68.79

# refinement stage
Car AP@0.70, 0.70, 0.70:
bbox AP:98.43, 90.39, 88.15
bev  AP:90.42, 88.99, 86.88
3d   AP:89.31, 79.08, 77.17

SUNRGBD dataset

Please follow the instruction here.

Note

Since we update our code from PyTorch-0.3.1 to PyTorch-1.0 and our code uses many random sampling operations, the results may be not exactly the same as those reported in our paper. But the difference should be +-0.5%, if you can not get the similar results, please contact me. I am still working to make results stable.

Our code is supported multiple GPUs for training, but now the training is very fast for small dataset, like KITTI, SUN-RGBD. All the steps will finish in one day on single GPU.

Acknowledgements

Part of the code was adapted from F-PointNets.

License

Our code is released under MIT license.

About

The PyTorch Implementation of F-ConvNet for 3D Object Detection

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published