Skip to content

Goingqs/TensorRT-SSD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

TensorRT-SSD-facedet

This code is sample to implement caffe-ssd.

This sample implements a fast face detector based on caffe-ssd framework.

This model can run more than 250fps on gtx1080ti!

The code has been tested by myself, it can help you learn about TensorRT API and ssd fast!

requirmets:

*1.TensorRT 4.0.1

*2.Cuda8.0 / Cuda9.0 and Cudnn 7.1

*3.OpenCV

about TensorRT Scale layer

Scale layer has been supported officially, but you must provide both scale param and bias param!!!

If you just provide scale params, it won't work!

about TensorRT Eltwise layer

Eltwise layer has been supported officially too, but you can only provide two blobs as input!!!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages