Data

Tools

Indexes

Applications

Experiments

Open Source Science

mmdetection3d_purelidar_toturial

The toturial of how to use mmdetection3d for the pure lidar data

https://github.com/raycas2017/mmdetection3d_purelidar_toturial

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

The toturial of how to use mmdetection3d for the pure lidar data

Basic Info
  • Host: GitHub
  • Owner: RayCAS2017
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 16.9 MB
Statistics
  • Stars: 7
  • Watchers: 1
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed over 3 years ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

利用MMDetection3D训练纯点云数据集

引言

利用MMDet3D训练一个纯点云数据的一种方法是先将标注文件转成kitti格式，再基于MMDet3D的KittyDataset类进行训练。该方法虽然简单，不需要对MMDet3D进行任何的增改，但kitti数据的3D框坐标系是相机坐标系，不是lidar坐标系，因此还需要额外构建lidar和相机的内外参矩阵，将3D点云标注工具标注的3D框转到相机坐标系，整个流程显得特别的冗余。该repo利用lidar标注文件，不需要转化为kitti格式，即可对纯点云数据进行训练。

点云标注工具

lidar点云标注工具采用的是SUSTechPOINTS

SUSTechPOINTS_UI

其标签格式如下

SUSTechPOINTS_lable

步骤：

1、数据集准备

需要准备的数据文件夹，包含点云bins、sustechpoint的标签文件labels、类别文件classnames.txt、以及训练和验证文件Samplesets或者Imagesets。

数据文件夹 datasets

类别文件 classnames

SampleSets或者ImageSets

samplesets

执行：

python ./tools/create_data_custom.py --root-path ./data/minikitti_sustech

2、生成中间文件

添加的脚本为： ./tools/create_data_custom.py ./tools/create_gt_database_custom.py 生成的文件有： train_annotaion.pkl val_annotation.pkl dbinfos_train.pkl gt_database 其中， trainannotaion.pkl和valannotation.pkl记录的信息格式为:

pickl_info

dbinfostrain.pkl和gtdatabase是截取的gt 3d框信息和数据，用于数据增强。

3、构建PureLidarDataset

写一个继承CustomDataset的数据集PureLidarDataset，主要是修改了CustomDataset中的评估方法

1）添加 ./mmdet3d/datasets/purelidar_dataset.py 需要在./mmdet3d/datasets/init.py中申明可见 dataset_init_

2)添加 ./mmdet3d/core/evaluation/purelidar_eval.py 需要在/mmdet3d/core/evaluation/init.py中申明可见 eval_init_

4、配置文件

1）configs/base/datasets/minikitti-3d-3class_custom.py

config_base

2)configs/pointpillars/hvpointpillarssecfpn6x8160eminikitti-3d-3classcustom.py

config_model

5、训练

./tools/train.py configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_minikitti-3d-3class_custom.py --work-dir outputs/pointpillars_minikitti_custom_debug --gpu-id 0

Owner

  • Name: Ray
  • Login: RayCAS2017
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMDetection3D Contributors"
title: "OpenMMLab's Next-generation Platform for General 3D Object Detection"
date-released: 2020-07-23
url: "https://github.com/open-mmlab/mmdetection3d"
license: Apache-2.0

GitHub Events

Total
  • Watch event: 3
  • Fork event: 1
Last Year
  • Watch event: 3
  • Fork event: 1

Dependencies

.github/workflows/build.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • codecov/codecov-action v1.0.10 composite
  • codecov/codecov-action v2 composite
.github/workflows/deploy.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
.github/workflows/lint.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v1 composite
docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/serve/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
requirements/build.txt pypi
requirements/docs.txt pypi
  • docutils ==0.16.0
  • m2r *
  • mistune ==0.8.4
  • myst-parser *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
requirements/mminstall.txt pypi
  • mmcv-full >=1.4.8,<=1.6.0
  • mmdet >=2.24.0,<=3.0.0
  • mmsegmentation >=0.20.0,<=1.0.0
requirements/optional.txt pypi
  • open3d *
  • spconv *
  • waymo-open-dataset-tf-2-1-0 ==1.2.0
requirements/readthedocs.txt pypi
  • mmcv >=1.4.8
  • mmdet >=2.24.0
  • mmsegmentation >=0.20.1
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • lyft_dataset_sdk *
  • networkx >=2.2,<2.3
  • numba ==0.53.0
  • numpy *
  • nuscenes-devkit *
  • plyfile *
  • scikit-image *
  • tensorboard *
  • trimesh >=2.35.39,<2.35.40
requirements/tests.txt pypi
  • asynctest * test
  • codecov * test
  • flake8 * test
  • interrogate * test
  • isort * test
  • kwarray * test
  • pytest * test
  • pytest-cov * test
  • pytest-runner * test
  • ubelt * test
  • xdoctest >=0.10.0 test
  • yapf * test
requirements.txt pypi
setup.py pypi