• 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
    迪恩网络公众号

Ghustwb/MobileNet-SSD-TensorRT: Accelerate mobileNet-ssd with tensorRT

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

Ghustwb/MobileNet-SSD-TensorRT

开源软件地址(OpenSource Url):

https://github.com/Ghustwb/MobileNet-SSD-TensorRT

开源编程语言(OpenSource Language):

C++ 67.7%

开源软件介绍(OpenSource Introduction):

MobileNet-SSD-TensorRT

To accelerate mobileNet-ssd with tensorRT

TensorRT-Mobilenet-SSD can run 50fps on jetson tx2


Requierments:

1.tensorRT4

2.cudnn7

3.opencv


Run:

cmake .
make
./build/bin/mobileNet

Reference:

https://github.com/saikumarGadde/tensorrt-ssd-easy

https://github.com/chuanqi305/MobileNet-SSD

I replaced depthwise with group_conv,because group_conv has been optimized in cudnn7

I retrianed mobileNet-SSD,my number of classfication is 5


TODO:

  • To save serialized model
  • To solve the bug of getting different result with same input
  • The bottleneck of time cost lies in the decoding of pictures. "imread" cost too much ,to resolve it.
  • To modify the architecture, decrease the time cost

If want to decrease the time cost of "imread",you could rebuild OpenCV[https://github.com/jetsonhacks/buildOpenCVTX2]

Added producer-consumer

The bug has been fixed

image




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