Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/braun-steven/dafne

Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".

https://github.com/braun-steven/dafne

Science Score: 20.0%

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

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ✓
    Committers with academic emails
    1 of 2 committers (50.0%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.3%) to scientific vocabulary

Keywords

anchor-free deep-learning machine-learning object-detection one-stage-detector oriented-object-detection
Last synced: 5 months ago · JSON representation

Repository

Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".

Basic Info
  • Host: GitHub
  • Owner: braun-steven
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 2.99 MB
Statistics
  • Stars: 61
  • Watchers: 1
  • Forks: 12
  • Open Issues: 1
  • Releases: 0
Topics
anchor-free deep-learning machine-learning object-detection one-stage-detector oriented-object-detection
Created over 4 years ago · Last pushed almost 4 years ago
Metadata Files
Readme License

README.md

DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection

Code for our Paper DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection.

PWC
PWC
PWC

Datasets

  • UCAS-AOD: https://hyper.ai/datasets/5419
  • DOTA 1.0/1.5: https://captain-whu.github.io/DOTA/index.html
  • HRSC2016: https://www.kaggle.com/guofeng/hrsc2016

Docker Setup

Use the Dockerfile to build the necessary docker image:

bash docker build -t dafne .

Training

Check out ./configs/pre-trained/ for different pre-defined configurations for the DOTA 1.0, DOTA 1.5, UCAS-AOD, and HRSC2016 datasets. Use these paths as argument for the --config-file option below.

With Docker

Use the ./tools/run.py helper to start running experiments

bash ./tools/run.py --gpus 0,1,2,3 --config-file ./configs/dota-1.0/1024.yaml

Without Docker

bash NVIDIA_VISIBLE_DEVICES=0,1,2,3 ./tools/plain_train_net.py --num-gpus 4 --config-file ./configs/dota-1.0/1024.yaml

Pre-Trained Weights

| Dataset | mAP (%) | Config | Weights | |----------|---------|-----------------------------------------------------------------|------------------------------------------------------------------------------------------------------------| | UCAS-AOD | 89.65 | ucasaodr101_ms | ucas-aod-r101-ms.pth | | HRSC2016 | 89.76 | hrscr50ms | hrsc-r50-ms.pth | | DOTA 1.0 | 76.95 | dota-1.0r101ms | dota-1.0-r101-ms.pth | | DOTA 1.5 | 71.99 | dota-1.5r101ms | dota-1.5-r101-ms.pth |

Pre-Trained Weights Usage with Docker

bash ./tools/run.py --gpus 0 --config-file <CONFIG_PATH> --opts "MODEL.WEIGHTS <WEIGHTS_PATH>"

Pre-Trained Weights Usage without Docker

bash NVIDIA_VISIBLE_DEVICES=0 ./tools/plain_train_net.py --num-gpus 1 --config-file <CONFIG_PATH> MODEL.WEIGHTS <WEIGHTS_PATH>

Cite

bibtex @misc{lang2021dafne, title={DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection}, author={Steven Lang and Fabrizio Ventola and Kristian Kersting}, year={2021}, eprint={2109.06148}, archivePrefix={arXiv}, primaryClass={cs.CV} }

Acknowledgments

  • Thanks to AdelaiDet for providing the initial FCOS implementation
  • Thanks to Detectron2 for providing a general object detection framework

Owner

  • Name: Steven Braun
  • Login: braun-steven
  • Kind: user
  • Company: @ml-research

PhD Student at the AIML Lab @ml-research, Technical University of Darmstadt

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Committers

Last synced: 10 months ago

All Time
  • Total Commits: 18
  • Total Committers: 2
  • Avg Commits per committer: 9.0
  • Development Distribution Score (DDS): 0.111
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Steven Lang s****z@g****m 16
Steven Lang s****g@c****e 2
Committer Domains (Top 20 + Academic)
cs.tu-darmstadt.de: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 15
  • Total pull requests: 0
  • Average time to close issues: 17 days
  • Average time to close pull requests: N/A
  • Total issue authors: 14
  • Total pull request authors: 0
  • Average comments per issue: 2.87
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Levaru (2)
  • aikeet2927 (1)
  • NJUSTghw (1)
  • Pranav110500 (1)
  • keshavoct98 (1)
  • sahilutekar (1)
  • adickskylar (1)
  • Goubeast (1)
  • 2324773711 (1)
  • HappyBahman (1)
  • yangkk2019 (1)
  • ulkuacil64 (1)
  • NjustWrunning (1)
  • ghost (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • adabelief-pytorch ==0.0.5
  • beautifulsoup4 ==4.10.0
  • iopath ==0.1.9
  • seaborn ==0.10.1
  • setproctitle ==1.1.10
  • shapely ==1.7.1
tools/prepare_dota/requirements.txt pypi
  • opencv-python ==4.5.4.60
  • pillow ==8.4.0
  • shapely ==1.8.0