[TRT] 2: [utils.cpp::checkMemLimit::380] Error Code 2: Internal Error (Assertion upperBound != 0 failed. Unknown embedded device

[hgddingjun]

Hi@dusty-nv，I reference https://github.com/dusty-nv/jetson-inference/blob/master/docs/building-repo-2.md build and install jetson-inference but when i try to run "./imagenet images/orange_0.jpg images/test/output_0.jpg" , the following error show up: ... [TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1 ... [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}, 12653},) [TRT] device GPU, failed to build CUDA engine [TRT] device GPU, failed to load networks/bvlc_googlenet.caffemodel [TRT] failed to load networks/bvlc_googlenet.caffemodel [TRT] imageNet -- failed to initialize. imagenet: failed to initialize imageNet PS：I downloaded the models(bvlc_googlenet.caffemodel...) and put networks directory in advance. Can you help me to solve the problem?

[hgddingjun]

i use jetson xavier nv hardware platform. jetpack sdk 4.6.1 Jetson_Linux_R32.7.1_aarch64.tbz2

[leeyunhome]

i use jetson xavier nv hardware platform. jetpack sdk 4.6.1 Jetson_Linux_R32.7.1_aarch64.tbz2

Hello, @hgddingjun

hello? May I know which carrier board you are using?

Thank you.

[ooijenvangilbert]

Hi, i am facing the same issue.

I am not running it from the docker container

My hardware is this setup : https://www.seeedstudio.com/Jetson-20-1-H2-p-5329.html jetpack 4.6.2 [L4T 32.7.2] cuda 10.2.300 TensorRt 8.2.1.8 cuDNN 8.2.1.32

[TRT] =============== Computing reformatting costs [TRT] *************** Autotuning Reformat: Float(307200,102400,320,1) -> Float(307200,1,960,3) *************** [TRT] --------------- Timing Runner: Optimizer Reformat(input_0 -> ) (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/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18.onnx [TRT] segNet -- failed to load. jetson.inference -- segNet failed to load network Traceback (most recent call last): File "/home/xavier/Desktop/pypro/Nvidia/Deep-learning/segnet.py", line 33, in net = jetson.inference.segNet('fcn-resnet18-voc')

[ooijenvangilbert]

Hi @dusty-nv

So i have a fresh docker container but inside and outside of the container running the same code i get this exception.

[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},)

Is there anything i can do to resolve this? do you need more info?

Thanks in advance

[dusty-nv]

Hi @ooijenvangilbert, I believe you need to reflash your Jetson Xavier NX 16GB or SD card with the latest JetPack 5.0.1 - https://forums.developer.nvidia.com/t/i-have-stucked-when-i-use-jetson-inference-on-xavier-nx-16gb/214020/5?u=dusty_nv

[ooijenvangilbert]

Hi @ooijenvangilbert, I believe you need to reflash your Jetson Xavier NX 16GB or SD card with the latest JetPack 5.0.1 - https://forums.developer.nvidia.com/t/i-have-stucked-when-i-use-jetson-inference-on-xavier-nx-16gb/214020/5?u=dusty_nv

Hi @dusty-nv , I had the intention to do so but the SDK manager software (the pretty UI one) already crashed on startup and I don't feel secure enough for the command line option. Will however dive into it and if needed start a new item.

[ooijenvangilbert]

Hi @ooijenvangilbert, I believe you need to reflash your Jetson Xavier NX 16GB or SD card with the latest JetPack 5.0.1 - https://forums.developer.nvidia.com/t/i-have-stucked-when-i-use-jetson-inference-on-xavier-nx-16gb/214020/5?u=dusty_nv

After a very lengthy route of getting ubuntu 22.04 off my dual boot laptop and 18.04 installed i managed to get the Xavier flashed and up and running, this issue is resolved with JetPack 5.0.1