Low fps when doing object detection on jetson nano

Autonomous Machines Jetson & Embedded Systems Jetson Nano
7

Hi,

An ONNX format is enough.

You can convert it to TensorRT engine with the following command:

$ /usr/src/tensorrt/bin/trtexec --onnx=[your/model] --saveEngine=model.trt

More, if half-precision is acceptable, you can also convert it with fp16 mode for better performance.

$ /usr/src/tensorrt/bin/trtexec --onnx=[your/model] --saveEngine=model.trt --fp16

Thanks.