PyTorch to TensorRT engine with TensorRT 3.0 on Jetson TX2?

Hi nVidia.

After the release of your latest JetPack 3.2 with TensorRT 3.0, do you support converting PyTorch models into TensorRT engines as described here: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/topics/topics/workflows/manually_construct_tensorrt_engine.html

The guide describes the conversion process using the Python API. Is the TensorRT Python API available on the Jetson now with this JetPack v3.2?
If not, are we able to convert PyTorch models using the C++ API?

Best regards
Thomas Jespersen

Hi,

PyTorch to TensorRT is not available for Jetson platform due to no Python API:

You can find our supported information here:
http://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#tensorrtworkflow

Thanks.