Moving from TX2 to Xavier NX struggle

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX
#1

Hi Guys,

I decided to try xaiver NX upgrading from TX2 but my software was developed using Jetpack 4.3 & tensorRT so faced challenges to get the machine learning partially working unfortunately!
The software is for detecting & tracking objects and after moving to Xavier NX the detection seems to be off for some reason.
My question:
How do we convert SSD-mobilenet model to tensorRT .UFF file on Jetpack 4.4 on the Jetson NX?

Any reason why the detection feature is interfered?

Thanks

#2

Any reply from an expert!

#4

Please don’t expect to get the response while the issue posted at weekend.

We will investigate to have the update soon. Thanks

#5

Hi,

Do you have any error or output log can share with us?

As UFF has been deprecated from TensorRT 8.0, it’s more recommended to use ONNX intermediate format instead.
Do you still have the original model format? ex. .pb or .h5?

Thanks.

#7

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