Use TensorRT API to implement Caffe-SSD, SSD(channel pruning), Mobilenet-SSD
#Introduction:
- The original Caffe-SSD can run 3-5fps on my jetson tx2.
- TensorRT-SSD can run 8-10fps on my jetson tx2.
- TensorRT-SSD(channel pruning) can run 15-16fps on my jetson tx2.
- TensorRT-Mobilenet-SSD can run 40-43fps on my jetson tx2(it‘s cool!), and run 90+fps on gtx1060.
#Requirements:
- TensorRT3.0
- Cuda8.0 or Cuda9.0
The code will be published shortly...