https://github.com/daybreak-u/thundernet_mmdetection
thundernet ncnn
https://github.com/daybreak-u/thundernet_mmdetection
ncnn thundernet
Last synced: 8 months ago
JSON representation
thundernet ncnn
- Host: GitHub
- URL: https://github.com/daybreak-u/thundernet_mmdetection
- Owner: DayBreak-u
- License: apache-2.0
- Created: 2021-02-06T12:25:38.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2021-02-20T09:53:15.000Z (over 5 years ago)
- Last Synced: 2025-02-25T09:13:40.851Z (over 1 year ago)
- Topics: ncnn, thundernet
- Language: Python
- Homepage:
- Size: 153 MB
- Stars: 43
- Watchers: 1
- Forks: 5
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MMDetection_Lite
基于[mmdetection](https://github.com/open-mmlab/mmdetection) 实现一些轻量级检测模型，安装方式和mmdeteciton相同
## voc0712
voc 0712训练 voc2007测试 coco预训练
thundernet_voc_shufflenetv2_1.5
| input shape | mAP |
|--------------------|:-------------:|
| 320*320 | 0.71 |
| 352*352 | 0.722 |
| 384*384 | 0.734 |
| 416*416 | 0.738 |
| 448*448 | 0.744 |
| 480*480 | 0.747 |
## coco2017
thundernet_coco_shufflenetv2_1.5
| input shape | AP(0.5:0.95) |
|--------------------|:-------------:|
| 320*320 | 0.22 |
## 移动端推理 ncnn project
[thundernet_ncnn](https://github.com/ouyanghuiyu/thundernet_ncnn)
## Get Started
Please see [GETTING_STARTED.md](docs/get_started.md) for the basic usage of MMDetection.
```
@article{mmdetection,
title = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
journal= {arXiv preprint arXiv:1906.07155},
year={2019}
}
```