Science Score: 26.0%

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

  • 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 (6.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Bovey0809
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 15.7 MB
Statistics
  • Stars: 2
  • Watchers: 2
  • Forks: 1
  • Open Issues: 1
  • Releases: 0
Created over 4 years ago · Last pushed over 4 years ago
Metadata Files
Readme Changelog Contributing License Code of conduct Citation Support

README.md

Merge Monster of Yolo & PointNet++ & CenterNet3D

Extract 2D image features from Yolo. Extract 3D features from PointNet++. Combine them as input for CenterNet3D's Head. Boom!

Build Env

NOTE: Please download and process the data according to mmdetction3d dataset prepare. Please assign you github token to GITHUB_TOKEN when you run docker build.

bash git clone https://github.com/Bovey0809/merge_monster_3d.git cd merge_monster_3d docker build --network=host -f docker/Dockerfile -t mergenet . --build-arg GITHUB_TOKEN=your_token docker run --gpus all --ipc=host -it -v $HOME/data:/mmdetection3d/data -v $HOME/work_dirs/:/mmdetection3d/work_dirs mergenet

TODOS

  • [x] PointNet feature extractor.
  • [x] 2D images feature map extractor.
  • [x] Single Training (mainly for debugging).
  • [x] Distribute Training
  • [x] Inference (For 3D Objects detection)
  • [x] Evaluation (Metric Map)
  • [x] NanoDet train, test, eval

Basic Script

Train

  • Single GPU(Debugging) bash python tools/train.py configs/mergenet/merge_net.py python tools/train.py configs/nanodet/nanodet.py
  • Multi gpus(8 gpus) bash ./tools/dist_train.sh configs/mergenet/merge_net.py 8 ./tools/dist_train.sh configs/nanodet/nanodet.py 8

Test

  • Single GPU(demo visualization) bash python tools/test.py configs/mergenet/merge_net.py weights/lastest.pth
  • Multi GPUS() bash ./tools/dist_test.sh configs/nanodet/nanodet.py weights.pth 8 --eval bbox or bash CUDA_VISIBLE_DEVICES=1,2,3,4 ./tools/dist_test.sh configs/nanodet/nanodet.py weights.pth 4 --eval bbox

Experiments

Network | config | dataset | result | script id --- | --- | --- | --- | --- CenterNet3D | mergenetvoxelvoxelencodermiddleencoder1x136epochssunrgbd.py | SunRGBD | mAP 20.0 | 1 NanodetTAN | nanodet.py | COCO | mAP 22.0 | 2

Simple Scripts for

  1. ./tools/train.py configs/mergenet/mergenetvoxelvoxelencodermiddleencoder1x136epochssunrgbd.py 8
  2. ./tools/disttest.sh configs/nanodet/nanodet.py ./weightschanged.pth 8 --eval bbox

Owner

  • Name: 背对疾风吧
  • Login: Bovey0809
  • Kind: user

GitHub Events

Total
Last Year

Dependencies

requirements/docs.txt pypi
  • docutils ==0.16.0
  • m2r *
  • myst-parser *
  • opencv-python *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
  • torch *
requirements/mminstall.txt pypi
  • mmcv-full >=1.3.8,<=1.4.0
  • mmdet >=2.14.0,<=3.0.0
  • mmsegmentation >=0.14.1,<=1.0.0
requirements/optional.txt pypi
  • open3d *
  • waymo-open-dataset-tf-2-1-0 ==1.2.0
requirements/readthedocs.txt pypi
  • mmcv *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • lyft_dataset_sdk *
  • networkx >=2.2,<2.3
  • numba ==0.48.0
  • numpy <1.20.0
  • 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