Kernel dies when converting model to TRT when running live_demo.ipynb

Hi, I’m encountering this problem when running live_demo.ipynb of trt_pose 2 Please help. ps:with Jetson Nano
as soon as I run the line

model_trt = torch2trt.torch2trt(model, [data], fp16_mode=True, max_workspace_size=1<<25

from the live_demo.ipynb, the whole kernel crashes,and the system just freeze.and this line can not finish.


Do you meet any error or crash log?

If just the system freeze, would you mind to wait it longer.
Since TensorRT conversion need to evaluation algorithm layer-by-layer, it might take times to finish.


This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.