• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

sufeidechabei/gluon-mobilenet-yolov3: Gluon-Mobilenet-yolov3

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

sufeidechabei/gluon-mobilenet-yolov3

开源软件地址(OpenSource Url):

https://github.com/sufeidechabei/gluon-mobilenet-yolov3

开源编程语言(OpenSource Language):

Python 100.0%

开源软件介绍(OpenSource Introduction):

Gluon-Mobilenet-YOLOv3

Paper

YOLOv3: An Incremental Improvement

Joseph Redmon, Ali Farhadi

Abstract
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that’s pretty swell. It’s a little bigger than last time but more accurate. It’s still fast though, don’t worry. At 320 × 320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 AP50 in 51 ms on a Titan X, compared to 57.5 AP50 in 198 ms by RetinaNet, similar performance but 3.8× faster. As always, all the code is online at https://pjreddie.com/yolo/.

[Paper] [Original Implementation]

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam

Abstract
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

[Paper] [Original Implementation]

Prerequisites

  1. Python 3.6 +
  2. Gluoncv 0.3.0
  3. Mxnet

Usage

Mobilenet

voc

python3 train_yolo3_mobilenet.py --network mobilenet1_0 --dataset voc --gpus 0,1,2,3,4,5,6,7 --batch-size 64 -j 16 --log-interval 100 --lr-decay-epoch 160,180 --epochs 200 --syncbn --warmup-epochs 4

coco

python3 train_yolo3_mobilenet.py --network mobilenet1_0 --dataset coco --gpus 0,1,2,3,4,5,6,7 --batch-size 64 -j 32 --log-interval 100 --lr-decay-epoch 220,250 --epochs 280 --syncbn --warmup-epochs 2 --mixup --no-mixup-epochs 20 --label-smooth --no-wd

MAP

Backbone GPU Dataset Size MAP
Mobilenet 8 Tesla v100 VOC random shape 76.12
Mobilenet 8 Tesla v100 COCO2017 random shape 28.3

Credit

@article{yolov3,
  title={YOLOv3: An Incremental Improvement},
  author={Redmon, Joseph and Farhadi, Ali},
  journal = {arXiv},
  year={2018}
}
@article{mobilenets,
  title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
  author={Andrew G. Howard, Menglong Zhu, Bo Chen,Dmitry Kalenichenko,Weijun Wang, Tobias Weyand,Marco Andreetto, Hartwig Adam},
  journal = {arXiv},
  year = {2017}
}



鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap