INT8 colibration Inference

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

Why does my Jetson Orin Nano 4GB crash when running the gen_calibration_cache.py code with the YOLOv8s model? The memory usage is very high, and if I use FP16, the inference process crashes. What should I do?

3

Hi,

Do you run out of memory?
Are you able to share the error log with us so we can give it a check?

Thanks.

4

“The issue is resolved. It was due to setting the work memory size too large during model inference. Thank you!”

5

Thanks for the update.

Good to know the issue is solved.

7

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