Troubleshooting TensorRT Engine Deserialization Issue: Null Engine

Robotics & Edge Computing Jetson & Embedded Systems Jetson Orin Nano
1

self.trt_logger = trt.Logger(trt.Logger.WARNING)
with open(“./yolox_tiny.trt”, “rb”) as f:
runtime = trt.Runtime(self.trt_logger)
self.engine = runtime.deserialize_cuda_engine(f.read())
self.context = self.engine.create_execution_context()

In this code, self.engine becomes null, and an error occurs at self.context = self.engine.create_execution_context(). Why does it become null? The file does exist

Jetpack : 5.1.2-b104,
cuda : 11.4
cudnn : 8.6
TensorRT : 8.2.1.8

4

Dear @gecreative.kasa,
Does this issue still need support?

5

Thank you for your answer.
I apologize, I forgot to confirm.
This issue has been resolved, so no further support is needed.
Thank you.

7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.