I have stucked When I use jetson-inference on xavier nx 16GB

[forumuser]

Hello, @dusty_nv

./detectnet-console.py images/airplane_0.jpg output_2.jpg

[TRT]    Local timing cache in use. Profiling results in this builder pass will not be stored.
[TRT]    Constructing optimization profile number 0 [1/1].
[TRT]    Reserving memory for activation tensors. Host: 0 bytes Device: 1082804 bytes
[TRT]    =============== Computing reformatting costs
[TRT]    *************** Autotuning Reformat: Float(270000,90000,300,1) -> Float(270000,1,900,3) ***************
[TRT]    --------------- Timing Runner: Optimizer Reformat(Input -> <out>) (Reformat)
[TRT]    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}, 12660},)
[TRT]    device GPU, failed to build CUDA engine
[TRT]    device GPU, failed to load networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff
[TRT]    detectNet -- failed to initialize.
jetson.inference -- detectNet failed to load network
Traceback (most recent call last):
  File "./detectnet-console.py", line 54, in <module>
    net = jetson.inference.detectNet(opt.network, sys.argv, opt.threshold)
Exception: jetson.inference -- detectNet failed to load network

[TRT]    Local timing cache in use. Profiling results in this builder pass will not be stored.
[TRT]    Constructing optimization profile number 0 [1/1].
[TRT]    Reserving memory for activation tensors. Host: 0 bytes Device: 802816 bytes
[TRT]    =============== Computing reformatting costs
[TRT]    *************** Autotuning Reformat: Float(150528,50176,224,1) -> Float(150528,1,672,3) ***************
[TRT]    --------------- Timing Runner: Optimizer Reformat(input_0 -> <out>) (Reformat)
[TRT]    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}, 12660},)
[TRT]    device GPU, failed to build CUDA engine
[TRT]    device GPU, failed to load networks/MonoDepth-FCN-Mobilenet/monodepth_fcn_mobilenet.onnx
depthNet -- failed to initialize.
depthnet:   failed to initialize depthNet
manager@manager-desktop:~/coding/jetson-inference/build/aarch64/bin$ ./depthnet "images/room_*.jpg" images/test/_depth_room_%i.jpg

Can you tell me how to resolve this errors?

Thank you.

[AastaLLL]

Hi,

There is an issue when using TensorRT on the Xavier NX 16GB platform.
We are actively working on this internally.

Will share more informaiton with you later.
Thanks.

[AastaLLL]

Hi,

Thanks for your patience.

The fix for TensorRT on Xavier NX 16GB board is available in the latest JetPack 5.0.1.
Please upgrade environment and trying it again.

Thanks.