Serializing the engine at the end of the network_api_pytorch_mnist/sample.py file produces segmentation fault

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hi,

I’m getting a segmentation fault in python3 when I serialize:

serialized_engine = engine.serialize()

Any advice?

Thanks,
Matthew

2

Just figured out it needed to be inside the with build_engine(weights) as engine statement. Works now!