Jeston Xavier NX 8GB version Model conversion sucess, but !6GB version Failed!

[colave]

The same model, using the same environment configuration, the only difference is that one is the 8GB version, and the other is the 16GB version. The former can convert the model correctly, while the latter will report an error.
The above image shows the 8GB version

[AastaLLL]

Hi,

This is a known issue.
The fix is aviable in JetPack 4.6.3 or JetPack 5.

TensorRT with Jetpack 4.6.2 on Xavier NX emmc 16gb version

Hi, i am trying to use tensorrt on a Xavier NX with emmc and 16gb ram and flashed Jetpack 4.6.1 and 4.6.2 onto it. Sadly the trt engine cannot be build from an onnx file… the following error message is outputted: [05/09/2022-10:29:16] [E] Error[2]: [utils.cpp::checkMemLimit::380] Error Code 2: Internal Error (Assertion upperBound != 0 failed. Unknown embedded device detected. Please update the table with the entry: {{1794, 6, 16}, 12653},) [05/09/2022-10:29:16] [E] Error[2]: [builder.cpp::b…

Thanks.