Sign inSign up

adioshun/voxelnet

By adioshun

•Updated almost 8 years ago

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection, Tensorflow

Image
0

1.2K

adioshun/voxelnet repository overview

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection가 구현된 도커 입니다.

⁠필요 작업 (데이터 다운로드, 폴더 생성)

└── data/dataset
       ├── training   <-- training data
       |   ├── image_2
       |   ├── label_2
       |   └── velodyne
       └── validation  <--- evaluation data  
       |   ├── image_2
       |   ├── label_2
       |   └── velodyne
⁠1. training 데이터는 아래 명령어로 생성
cd /voxelnet/data/dataset
wget https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_calib.zip
wget https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_velodyne.zip
wget https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_label_2.zip
wget https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_image_2.zip
unzip *
# training 폴더 생성과 하단에 image_2, label_2, velodyne생성 확인
⁠2. training 데이터는 아래 명령어로 생성
ln -s training validation

동작 테스트를 위한 임시 방편

⁠실행

python3 /voxelnet/train.py
python3 /voxelnet/test.py

jupyter notebook with tensorboard 설치 되어있음

Tag summary

Content type

Image

Digest

Size

2.2 GB

Last updated

almost 8 years ago

docker pull adioshun/voxelnet