Skip to content

Latest commit

 

History

History
17 lines (11 loc) · 498 Bytes

README.md

File metadata and controls

17 lines (11 loc) · 498 Bytes

TensorRT-SSD

Use TensorRT API to implement Caffe-SSD, SSD(channel pruning), Mobilenet-SSD

#Introduction:

  1. The original Caffe-SSD can run 3-5fps on my jetson tx2.
  2. TensorRT-SSD can run 8-10fps on my jetson tx2.
  3. TensorRT-SSD(channel pruning) can run 15-16fps on my jetson tx2.
  4. TensorRT-Mobilenet-SSD can run 40-43fps on my jetson tx2(it‘s cool!), and run 90+fps on gtx1060.

#Requirements:

  1. TensorRT3.0
  2. Cuda8.0 or Cuda9.0

The code will be published shortly...