How do you train a DNN model?

Autonomous Vehicles DRIVE AGX Xavier DRIVE AGX Xavier General
1

Please provide the following info (check/uncheck the boxes after clicking “+ Create Topic”):
Software Version
DRIVE OS Linux 5.2.0
DRIVE OS Linux 5.2.0 and DriveWorks 3.5
NVIDIA DRIVE™ Software 10.0 (Linux)
NVIDIA DRIVE™ Software 9.0 (Linux)
other DRIVE OS version
other

Target Operating System
Linux
QNX
other

Hardware Platform
NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
NVIDIA DRIVE™ AGX Pegasus DevKit (E3550)
other

SDK Manager Version
1.4.1.7402
other

Host Machine Version
native Ubuntu 18.04
other
Hi,
Please answer the following questions:

  1. Can we train on AGX PEGASUS board or the Model is trained on host device and converted to Tensorrt model?
  2. How can we deploy our custom model on Pegasus?

Thank you,
Daniel.

3

Dear @daniel.vadranapu1,

  1. The Pegasus board is to perform inference. You can prepare your model on host and convert to TensorRT model on pegasus.
  2. If your customer model can be converted to ONNX on host, you can convert ONNX → TensorRT on target and use TensorRT model to perform inference. Please check TensorRT Developer Guide :: Deep Learning SDK Documentation for importing ONNX model
1 Like