TensorRT help for beginners

Hi there,

I’m a computer science student and I’d like to learn about the different AI solutions. Trying to get an overview about different possibilities to transform a trained network to an embedded system, I learned about TensorRT. My question now is: To what extend does it support pruning and quantisation?

Thanks in advance and sorry if my question is very basic, I just started getting into this subject.

Best,
Samir

Hello,

regarding TRT quantisation and pruning support, recommend reviewing http://on-demand.gputechconf.com/gtc/2017/presentation/s7310-8-bit-inference-with-tensorrt.pdf