Error with docker container folowing DLI course - starting with jetson nano

Hello , i’m trying to follow the beginner course " getting started with AI on jetson nano " with a xavier nx board but i get errors frequently . it is a nightmare just to follow the setup section of the course.
Board : Xavier NX - jetpack 5.1 [ L4T 35.2.1 ]

Below the error i get after running these commands copied from the videocourse :

# create a reusable script
echo "sudo docker run --runtime nvidia -it --rm --network host \
    --volume ~/nvdli-data:/nvdli-nano/data \
    --device /dev/video0 \
    nvcr.io/nvidia/dli/dli-nano-ai:v2.0.2-r32.7.1" > docker_dli_run.sh

# make the script executable
chmod +x docker_dli_run.sh

# run the script
./docker_dli_run.sh

docker: Error response from daemon: Unknown runtime specified nvidia.
See ‘docker run --help’.

Does it make a difference using a Xavier NX compared to a Nano ?

I also installed docker with : sudo apt install docker.io due to the fact i got an error about "docker command not found "

Hi,

The course is for JetPack 4 users and won’t work on the JetPack 5 environment.

You can check our jetson-inference tutorial instead:

Thanks.

ok thank you !
if i want to get the certification what should i do ? should i downgrade the jetpack version ( if possible ) or there are other ways to get the certifiation with my jetson xavier nx?

Hi @eracle94, you can find the Xavier NX SD card images for JetPack 4 here: https://developer.nvidia.com/embedded/downloads#?search=jetson%20xavier%20nx%20developer%20kit%20sd%20card%20image

Do you mean the DLI certification for that particular course, or the Jetson AI Specialist certification? If the later, given the circumstances you can skip the DLI course and do the Hello AI World instead.

yes, i mean the jetson ai specialist certification

So from what i understood i have two option to get the certification " jetson ai specialist " :
1 ) download the "Jetson Xavier NX Developer Kit SD Card Image 4.6.1 " because i don’t see the 4.0 , should still work even it is 4.6.1 , right? and follow the fundamental course and getting started with ai on jetosn nano and then project based assesment as i was trying to do until now.
2 ) skip " jetson ai fundamentals course " and " getting started with ai on jetson nano DLI course certificate and only do the " hello ai world instead ".

am i correct?

Yes, for the JetPack 4.6.1 SD card image, you should be able to run the nvcr.io/nvidia/dli/dli-nano-ai:v2.0.2-r32.7.1 DLI container.

Yes, given the circumstances of you using Xavier NX, you can skip the DLI and do the Hello AI World. You can base your project on the Hello AI World or some other project using PyTorch/TensorFlow/ect. I review/approve the Jetson AI Specialist applications so it’s okay.

Thank you very much … but i still get errors after running the command in the hello world course ( running container ) . page : jetson-inference/aux-docker.md at master · dusty-nv/jetson-inference · GitHub

git clone --recursive https://github.com/dusty-nv/jetson-inference
cd jetson-inference
docker/run.sh


i don’t know what it’s doing and it is not the same as the video course shows
i also tried running some code found online to resolve the problem but it doesn’t work for me :

sudo apt install -y nvidia-docker2
sudo systemctl daemon-reload
sudo systemctl restart docker

Should i reset the jetson xavier board and start from zero ? how to reset the board to factory settings ? it gives me too many problem for it to be a beginner course

Hi @eracle94, I can’t see from your screenshot what the error is - please try copy and pasting the text output from the terminal. Also, if you are using the JetPack SD card image for Xavier NX, you shouldn’t need to install the docker components yourself - so you may want to try re-flashing your SD card.

HI , i’m using the a205 carrier board with nvidia xavier nx and when i run /docker/run.sh :

ARCH:  aarch64
reading L4T version from /etc/nv_tegra_release
L4T BSP Version:  L4T R35.2.1
[sudo] password for jetson-poc: 
CONTAINER:      dustynv/jetson-inference:r35.2.1
DATA_VOLUME:    --volume /home/jetson-poc/jetson-inference/data:/jetson-inference/data --volume /home/jetson-poc/jetson-inference/python/training/classification/data:/jetson-inference/python/training/classification/data --volume /home/jetson-poc/jetson-inference/python/training/classification/models:/jetson-inference/python/training/classification/models --volume /home/jetson-poc/jetson-inference/python/training/detection/ssd/data:/jetson-inference/python/training/detection/ssd/data --volume /home/jetson-poc/jetson-inference/python/training/detection/ssd/models:/jetson-inference/python/training/detection/ssd/models
USER_VOLUME:    
USER_COMMAND:   
V4L2_DEVICES:   
DISPLAY_DEVICE:  
Unable to find image 'dustynv/jetson-inference:r35.2.1' locally
r35.2.1: Pulling from dustynv/jetson-inference
f04b4bbe1580: Pulling fs layer 
0a1def070f0b: Pulling fs layer 
0a1def070f0b: Extracting [==================================================>]  234.2MB/234.2MB
6328a89a71f9: Waiting 
f7adbdc55099: Waiting 
4d9a358decc4: Waiting 
3dfc1c856868: Pulling fs layer 
3dfc1c856868: Waiting 
acffb039d986: Pulling fs layer 
cb612f8e41f4: Pulling fs layer 
ef8e5ac0e0fe: Waiting 
b25e20cd391d: Pulling fs layer 
3e8e9bd0cf8c: Downloading [==================================================>]  2.378GB/2.378GB
8455eaf2ad8c: Downloading [==================================================>]   1.49GB/1.49GB
de9760151109: Download complete 
7b33b2edf791: Download complete 
15b2eaee62f4: Download complete 
3b4c3d0caa22: Download complete 
249cd5425951: Download complete 
db647cb5fe6c: Download complete 
a692693c4aa7: Download complete 
cc31f854225f: Download complete 
c9881e948b12: Download complete 
6eb6de2d9d95: Download complete 
d955bda23ac2: Download complete 
c417faa82118: Download complete 
034e642ed98e: Download complete 
9e8a99aa6616: Download complete 
a0755e308026: Download complete 
fc2a243718a3: Download complete 
2974057b6b3e: Download complete 
caa6e94b90bd: Download complete 
f3d6fb7b5668: Download complete 
fd2d18fde7a9: Download complete 
b666c3392147: Download complete 
9029af33b5d8: Download complete 
f7cffb8e669c: Download complete 
a1e885b18900: Download complete 
e159154ecb01: Download complete 
fe682f298222: Download complete 
7b3b3ffa484a: Download complete 
1dd4dc634b84: Download complete 
6ba25abe7bec: Download complete 
11601547ab34: Download complete 
a614bf5470e6: Download complete 
860c0bb72c0b: Download complete 
9780b10ffc37: Download complete 
54a570ae2194: Download complete 
fdf10992fe28: Download complete 
a6394c9a5cbd: Download complete 
83a71f5272f4: Download complete 
ac82d2c316e4: Download complete 
3eac585f8ef5: Download complete 
c8e6f1170e80: Download complete 
d4864be51eb9: Download complete 
c01a4564b30d: Download complete 
docker: write /var/lib/docker/tmp/GetImageBlob1219555402: no space left on device.
See 'docker run --help'.

the os system is stored on an internal memory of the board but i need more memory , so i need to install the jetpack image on external sdcard. If i want to do the "Hello world " course i need more memory.
Also my SDcard is not recognized , why ?
Also what do you mean " Also, if you are using the JetPack SD card image for Xavier NX, you shouldn’t need to install the docker components yourself "
SIncerely , i dont know what i have to do …

Hi @eracle94, can follow a guide like this to relocate the docker data root to another drive: https://www.ibm.com/docs/en/z-logdata-analytics/5.1.0?topic=compose-relocating-docker-root-directory

Just make sure that this drive gets mounted at boot (i.e. in /etc/fstab), otherwise when the docker daemon starts the drive won’t be mounted yet.

The SD card images already come with all the JetPack components pre-installed, including Docker and the NVIDIA Container Runtime.

hi @dusty_nv , i managed to reinstall the os in the external sd card but i still get this error when i run "/docker/run.sh "

jetson-poc@ubuntu:~/jetson-inference$ docker/run.sh
ARCH:  aarch64
reading L4T version from /etc/nv_tegra_release
L4T BSP Version:  L4T R35.1.0
[sudo] password for jetson-poc: 
CONTAINER:      dustynv/jetson-inference:r35.1.0
DATA_VOLUME:    --volume /home/jetson-poc/jetson-inference/data:/jetson-inference/data --volume /home/jetson-poc/jetson-inference/python/training/classification/data:/jetson-inference/python/training/classification/data --volume /home/jetson-poc/jetson-inference/python/training/classification/models:/jetson-inference/python/training/classification/models --volume /home/jetson-poc/jetson-inference/python/training/detection/ssd/data:/jetson-inference/python/training/detection/ssd/data --volume /home/jetson-poc/jetson-inference/python/training/detection/ssd/models:/jetson-inference/python/training/detection/ssd/models
USER_VOLUME:    
USER_COMMAND:   
V4L2_DEVICES:   
localuser:root being added to access control list
DISPLAY_DEVICE: -e DISPLAY=:1 -v /tmp/.X11-unix/:/tmp/.X11-unix
unexpected fault address 0x24001d3fc28
fatal error: fault
[signal SIGSEGV: segmentation violation code=0x1 addr=0x24001d3fc28 pc=0xaaaab3c08654]

goroutine 1 [running, locked to thread]:
runtime.throw({0xaaaab4d05f73?, 0xaaaab494bed0?})
	/usr/lib/go-1.18/src/runtime/panic.go:992 +0x50 fp=0x400025f5e0 sp=0x400025f5b0 pc=0xaaaab3bf8550
runtime.sigpanic()
	/usr/lib/go-1.18/src/runtime/signal_unix.go:825 +0x1a4 fp=0x400025f610 sp=0x400025f5e0 pc=0xaaaab3c0eb44
runtime: unexpected return pc for runtime.doInit called from 0xaaaab528bc40
stack: frame={sp:0x400025f620, fp:0x400025f760} stack=[0x4000220000,0x4000260000)
0x000000400025f520:  0x0000000000000001  0x000000400025f568 
0x000000400025f530:  0x0000aaaab3bfa5a0 <runtime.printstring+0x0000000000000050>  0x0000aaaab4f98d40 
0x000000400025f540:  0x0000000000000001  0x0000000000000001 
0x000000400025f550:  0x0000aaaab3c0eb2c <runtime.sigpanic+0x000000000000018c>  0x000000400025f568 
0x000000400025f560:  0x0000aaaab3bf8730 <runtime.fatalthrow+0x0000000000000040>  0x000000400025f5a8 
0x000000400025f570:  0x0000aaaab3bf8550 <runtime.throw+0x0000000000000050>  0x000000400025f588 
0x000000400025f580:  0x0000000000000001  0x0000aaaab3bf8750 <runtime.fatalthrow.func1+0x0000000000000000> 
0x000000400025f590:  0x00000040000021a0  0x0000aaaab3bf8550 <runtime.throw+0x0000000000000050> 
0x000000400025f5a0:  0x000000400025f5b0  0x000000400025f5d8 
0x000000400025f5b0:  0x0000aaaab3c0eb44 <runtime.sigpanic+0x00000000000001a4>  0x000000400025f5c0 
0x000000400025f5c0:  0x0000aaaab3bf8570 <runtime.throw.func1+0x0000000000000000>  0x0000aaaab4d05f73 
0x000000400025f5d0:  0x0000000000000005  0x000000400025f568 
0x000000400025f5e0:  0x0000aaaab3c08654 <runtime.doInit+0x0000000000000064>  0x0000aaaab4d05f73 
0x000000400025f5f0:  0x0000aaaab494bed0 <github.com/docker/cli/vendor/github.com/googleapis/gnostic/OpenAPIv2.init.1+0x0000000000000070>  0x0000024001d3fc28 
0x000000400025f600:  0x00000040000021a0  0x000000400025f688 
0x000000400025f610:  0x0000aaaab3c08660 <runtime.doInit+0x0000000000000070>  0x0f00aaaab539a318 
0x000000400025f620: <0x0000aaaab528bc40  0x0fa7e822e4c3f859 
0x000000400025f630:  0x0000aaaab5384b18  0x0000aaaab528bc40 
0x000000400025f640:  0x0000000000000000  0x0000aaaab528bc40 
0x000000400025f650:  0x000000400017dcd0  0x000000400025f6a8 
0x000000400025f660:  0x0000aaaab3c08728 <runtime.doInit+0x0000000000000138>  0x0000aaaab5128780 
0x000000400025f670:  0x000000400035c091  0x0000aaaab4d27fa9 
0x000000400025f680:  0x0000000000000019  0x0000aaaab5384b18 
0x000000400025f690:  0x0000aaaab60b5588  0x0000aaaab60b5588 
0x000000400025f6a0:  0x0000aaaab60e42e0  0x000000400025f7e8 
0x000000400025f6b0:  0x0000aaaab3c08660 <runtime.doInit+0x0000000000000070>  0x0000aaaab60b5520 
0x000000400025f6c0:  0x000000400025f6f8  0x0000000000000003 
0x000000400025f6d0:  0x000000400047eb60  0x0000aaaab5379460 
0x000000400025f6e0:  0x000000400047ecb0  0x0000000000000000 
0x000000400025f6f0:  0x000000400047eb60  0x0000000000000002 
0x000000400025f700:  0x0000000000000002  0x0000000000000000 
0x000000400025f710:  0x0000000000000000  0x0000aaaab5379370 
0x000000400025f720:  0x0000004000484840  0x000000400025f768 
0x000000400025f730:  0x0000aaaab44b4f54 <github.com/docker/cli/vendor/k8s.io/apimachinery/pkg/runtime.(*SchemeBuilder).AddToScheme-fm+0x0000000000000034>  0x000000400047eb60 
0x000000400025f740:  0x0000004000122e80  0x0000000000000000 
0x000000400025f750:  0x0000000000000001  0x000000400011a630 
0x000000400025f760: >0x000000400047eb60  0x000000400025f788 
0x000000400025f770:  0x0000aaaab48e1304 <github.com/docker/cli/vendor/github.com/docker/compose-on-kubernetes/api/client/clientset/scheme.AddToScheme+0x0000000000000064>  0x0000aaaab537c9d0 
0x000000400025f780:  0x000000400012ff40  0x000000400025f7a8 
0x000000400025f790:  0x0000aaaab48e1280 <github.com/docker/cli/vendor/github.com/docker/compose-on-kubernetes/api/client/clientset/scheme.init.0+0x0000000000000050>  0x0000aaaab537cb38 
0x000000400025f7a0:  0x000000400047eb60  0x000000400025f7e8 
0x000000400025f7b0:  0x0000aaaab3c08728 <runtime.doInit+0x0000000000000138>  0x0000004000111890 
0x000000400025f7c0:  0x0000000000000000  0x0000000000000003 
0x000000400025f7d0:  0x0000aaaab60b2700  0x0000aaaab60b26f0 
0x000000400025f7e0:  0x0000004000143ac0  0x000000400025f928 
0x000000400025f7f0:  0x0000aaaab3c08660 <runtime.doInit+0x0000000000000070>  0x0000aaaab60c13a0 
0x000000400025f800:  0x0800aaaab5129920  0x00000040004681a0 
0x000000400025f810:  0x08a306332b878ea5  0x3b0000400025f858 
0x000000400025f820:  0x0000aaaab3ef9c10 <github.com/docker/cli/vendor/github.com/gogo/protobuf/proto.RegisterType+0x0000000000000180>  0x0000000000000000 
0x000000400025f830:  0x0000004000458754  0x0000000000000001 
0x000000400025f840:  0x0000000000000010  0x0000000000000000 
0x000000400025f850:  0x0000000000000000  0x000000400025f918 
runtime.doInit(0x400025f788)
	/usr/lib/go-1.18/src/runtime/proc.go:6198 +0x64 fp=0x400025f760 sp=0x400025f620 pc=0xaaaab3c08654

goroutine 19 [chan receive]:
github.com/docker/cli/vendor/k8s.io/klog.(*loggingT).flushDaemon(0x0?)
	/build/docker.io-jIHXvt/docker.io-20.10.21/.gopath/src/github.com/docker/cli/vendor/k8s.io/klog/klog.go:1010 +0x60
created by github.com/docker/cli/vendor/k8s.io/klog.init.0
	/build/docker.io-jIHXvt/docker.io-20.10.21/.gopath/src/github.com/docker/cli/vendor/k8s.io/klog/klog.go:411 +0x148

why i don’t get the interface like in the first video of hello world course on youtube?

Hmm, I can’t say that I have seen this error before… did you happen to install Kubernetes (K8S) by chance? I see references to that later in the stack trace, but not sure if it’s related or not.

Are you able to run other L4T containers on your device?

sudo docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/l4t-base:r35.1.0

Hello , i’ve tried your code and seem to be similar to the video course ( but i still don’t get the GUI interface of the AI models as shown above ):



what do i have to do next?

i’ve also tried re-run the ./docker/run.sh and something has been downloaded ( GB of files , with unknown names like in the picture above ) but still no GUI interface with all the models . I guess maybe i 've downloaded all the pretrained models ?
if i go to /data/networks it has only few files and it doesn’t look the same as shown in the video

  • it seems that i have all the images in the image folder( animals , fruits … )
  • the video stream is working ( usb camera ) but …

when i run " detectnet /dev/video0 " i get this error :

root@ubuntu:/jetson-inference# detectnet /dev/video0
[gstreamer] initialized gstreamer, version 1.16.3.0
[gstreamer] gstCamera -- attempting to create device v4l2:///dev/video0
[gstreamer] gstCamera -- found v4l2 device: Stereo Vision 1: Stereo Vision 
[gstreamer] v4l2-proplist, device.path=(string)/dev/video0, udev-probed=(boolean)false, device.api=(string)v4l2, v4l2.device.driver=(string)uvcvideo, v4l2.device.card=(string)"Stereo\ Vision\ 1:\ Stereo\ Vision\ ", v4l2.device.bus_info=(string)usb-3610000.xhci-2.1, v4l2.device.version=(uint)330344, v4l2.device.capabilities=(uint)2225078273, v4l2.device.device_caps=(uint)69206017;
[gstreamer] gstCamera -- found 14 caps for v4l2 device /dev/video0
[gstreamer] [0] video/x-raw, format=(string)YUY2, width=(int)1280, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 10/1, 5/1 };
[gstreamer] [1] video/x-raw, format=(string)YUY2, width=(int)960, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 10/1, 5/1 };
[gstreamer] [2] video/x-raw, format=(string)YUY2, width=(int)800, height=(int)600, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction)15/1;
[gstreamer] [3] video/x-raw, format=(string)YUY2, width=(int)640, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] [4] video/x-raw, format=(string)YUY2, width=(int)640, height=(int)360, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction)31/1;
[gstreamer] [5] video/x-raw, format=(string)YUY2, width=(int)352, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] [6] video/x-raw, format=(string)YUY2, width=(int)320, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] [7] image/jpeg, width=(int)1280, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 15/1 };
[gstreamer] [8] image/jpeg, width=(int)960, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 15/1 };
[gstreamer] [9] image/jpeg, width=(int)800, height=(int)600, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction)30/1;
[gstreamer] [10] image/jpeg, width=(int)640, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] [11] image/jpeg, width=(int)640, height=(int)360, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction)60/1;
[gstreamer] [12] image/jpeg, width=(int)352, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] [13] image/jpeg, width=(int)320, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 15/1 };
[gstreamer] gstCamera -- selected device profile:  codec=MJPEG format=unknown width=1280 height=720
[gstreamer] gstCamera pipeline string:
[gstreamer] v4l2src device=/dev/video0 do-timestamp=true ! image/jpeg, width=(int)1280, height=(int)720 ! jpegdec name=decoder ! video/x-raw ! appsink name=mysink sync=false
[gstreamer] gstCamera successfully created device v4l2:///dev/video0
[video]  created gstCamera from v4l2:///dev/video0
------------------------------------------------
gstCamera video options:
------------------------------------------------
  -- URI: v4l2:///dev/video0
     - protocol:  v4l2
     - location:  /dev/video0
  -- deviceType: v4l2
  -- ioType:     input
  -- codec:      MJPEG
  -- codecType:  cpu
  -- width:      1280
  -- height:     720
  -- frameRate:  30
  -- numBuffers: 4
  -- zeroCopy:   true
  -- flipMethod: none
------------------------------------------------
[OpenGL] glDisplay -- X screen 0 resolution:  1920x1080
[OpenGL] glDisplay -- X window resolution:    1920x1080
[OpenGL] glDisplay -- display device initialized (1920x1080)
[video]  created glDisplay from display://0
------------------------------------------------
glDisplay video options:
------------------------------------------------
  -- URI: display://0
     - protocol:  display
     - location:  0
  -- deviceType: display
  -- ioType:     output
  -- width:      1920
  -- height:     1080
  -- frameRate:  0
  -- numBuffers: 4
  -- zeroCopy:   true
------------------------------------------------
[TRT]    downloading model SSD-Mobilenet-v2.tar.gz...
cd /usr/local/bin/networks ; wget --quiet --show-progress --progress=bar:force:noscroll --no-check-certificate https://nvidia.box.com/shared/static/jcdewxep8vamzm71zajcovza938lygre.gz -O SSD-Mobilenet-v2.tar.gz ; tar -xzvf SSD-Mobilenet-v2.tar.gz ; rm SSD-Mobilenet-v2.tar.gz
SSD-Mobilenet-v2.ta 100%[===================>]  59.61M  8.23MB/s    in 7.3s    
SSD-Mobilenet-v2/
SSD-Mobilenet-v2/ssd_coco_labels.txt
SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff
[TRT]    downloaded model SSD-Mobilenet-v2.tar.gz

detectNet -- loading detection network model from:
          -- model        networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff
          -- input_blob   'Input'
          -- output_blob  'NMS'
          -- output_count 'NMS_1'
          -- class_labels networks/SSD-Mobilenet-v2/ssd_coco_labels.txt
          -- threshold    0.500000
          -- batch_size   1

[TRT]    TensorRT version 8.4.1
[TRT]    loading NVIDIA plugins...
[TRT]    Registered plugin creator - ::GridAnchor_TRT version 1
[TRT]    Registered plugin creator - ::GridAnchorRect_TRT version 1
[TRT]    Registered plugin creator - ::NMS_TRT version 1
[TRT]    Registered plugin creator - ::Reorg_TRT version 1
[TRT]    Registered plugin creator - ::Region_TRT version 1
[TRT]    Registered plugin creator - ::Clip_TRT version 1
[TRT]    Registered plugin creator - ::LReLU_TRT version 1
[TRT]    Registered plugin creator - ::PriorBox_TRT version 1
[TRT]    Registered plugin creator - ::Normalize_TRT version 1
[TRT]    Registered plugin creator - ::ScatterND version 1
[TRT]    Registered plugin creator - ::RPROI_TRT version 1
[TRT]    Registered plugin creator - ::BatchedNMS_TRT version 1
[TRT]    Registered plugin creator - ::BatchedNMSDynamic_TRT version 1
[TRT]    Registered plugin creator - ::BatchTilePlugin_TRT version 1
[TRT]    Could not register plugin creator -  ::FlattenConcat_TRT version 1
[TRT]    Registered plugin creator - ::CropAndResize version 1
[TRT]    Registered plugin creator - ::CropAndResizeDynamic version 1
[TRT]    Registered plugin creator - ::DetectionLayer_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_ONNX_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_Explicit_TF_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_Implicit_TF_TRT version 1
[TRT]    Registered plugin creator - ::ProposalDynamic version 1
[TRT]    Registered plugin creator - ::Proposal version 1
[TRT]    Registered plugin creator - ::ProposalLayer_TRT version 1
[TRT]    Registered plugin creator - ::PyramidROIAlign_TRT version 1
[TRT]    Registered plugin creator - ::ResizeNearest_TRT version 1
[TRT]    Registered plugin creator - ::Split version 1
[TRT]    Registered plugin creator - ::SpecialSlice_TRT version 1
[TRT]    Registered plugin creator - ::InstanceNormalization_TRT version 1
[TRT]    Registered plugin creator - ::InstanceNormalization_TRT version 2
[TRT]    Registered plugin creator - ::CoordConvAC version 1
[TRT]    Registered plugin creator - ::DecodeBbox3DPlugin version 1
[TRT]    Registered plugin creator - ::GenerateDetection_TRT version 1
[TRT]    Registered plugin creator - ::MultilevelCropAndResize_TRT version 1
[TRT]    Registered plugin creator - ::MultilevelProposeROI_TRT version 1
[TRT]    Registered plugin creator - ::NMSDynamic_TRT version 1
[TRT]    Registered plugin creator - ::PillarScatterPlugin version 1
[TRT]    Registered plugin creator - ::VoxelGeneratorPlugin version 1
[TRT]    Registered plugin creator - ::MultiscaleDeformableAttnPlugin_TRT version 1
[TRT]    detected model format - UFF  (extension '.uff')
[TRT]    desired precision specified for GPU: FASTEST
[TRT]    requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT]    Unable to determine GPU memory usage
[TRT]    Unable to determine GPU memory usage
[TRT]    [MemUsageChange] Init CUDA: CPU +57, GPU +0, now: CPU 88, GPU 0 (MiB)
[TRT]    CUDA initialization failure with error: 999. Please check your CUDA installation:  http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html
[TRT]    DetectNativePrecisions() failed to create TensorRT IBuilder instance
[TRT]    selecting fastest native precision for GPU:  FP32
[TRT]    could not find engine cache /usr/local/bin/networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff.1.1.8401.GPU.FP32.engine
[TRT]    cache file invalid, profiling network model on device GPU
[TRT]    Unable to determine GPU memory usage
[TRT]    Unable to determine GPU memory usage
[TRT]    [MemUsageChange] Init CUDA: CPU +22, GPU +0, now: CPU 121, GPU 0 (MiB)
[TRT]    CUDA initialization failure with error: 999. Please check your CUDA installation:  http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html
Segmentation fault (core dumped)

Hi @eracle94, it seems there is something going wrong with your CUDA drivers (which is causing the process to exit prematurely before the GUI window is opened). You had mentioned earlier installing docker package yourself, which I’m not sure is a factor or not.

Which version of JetPack-L4T are you currently running? Here is what I would recommend:

(1) try building jetson-inference from source (outside of container) and see if you can get CUDA running like that: https://github.com/dusty-nv/jetson-inference/blob/master/docs/building-repo-2.md

(2) if that doesn’t work, reflash your Xavier NX SD card with the latest JetPack image (JetPack 5.1.1)

thanks for the help ,
jetpack 5.0.2 , L4T version : 35.1.0 as shown in the previous screenshot
is having two cores turned off a problem ? you can see it in the screenshot above
ok , i’ll try your suggestions , thanks again.

i’ve tried the first option but still doesn’t work , i run imagenet commands " ./imagenet images/orange_0.jpg images/test/output_0.jpg "

jetson-poc@ubuntu:~/jetson-inference/build/aarch64/bin$ ./imagenet images/orange_0.jpg images/test/output_0.jpg 
[video]  created imageLoader from file:///home/jetson-poc/jetson-inference/build/aarch64/bin/images/orange_0.jpg
------------------------------------------------
imageLoader video options:
------------------------------------------------
  -- URI: file:///home/jetson-poc/jetson-inference/build/aarch64/bin/images/orange_0.jpg
     - protocol:  file
     - location:  images/orange_0.jpg
     - extension: jpg
  -- deviceType: file
  -- ioType:     input
  -- codec:      unknown
  -- codecType:  v4l2
  -- frameRate:  0
  -- numBuffers: 4
  -- zeroCopy:   true
  -- flipMethod: none
  -- loop:       0
------------------------------------------------
[video]  created imageWriter from file:///home/jetson-poc/jetson-inference/build/aarch64/bin/images/test/output_0.jpg
------------------------------------------------
imageWriter video options:
------------------------------------------------
  -- URI: file:///home/jetson-poc/jetson-inference/build/aarch64/bin/images/test/output_0.jpg
     - protocol:  file
     - location:  images/test/output_0.jpg
     - extension: jpg
  -- deviceType: file
  -- ioType:     output
  -- codec:      unknown
  -- codecType:  v4l2
  -- frameRate:  0
  -- bitRate:    0
  -- numBuffers: 4
  -- zeroCopy:   true
------------------------------------------------
[OpenGL] glDisplay -- X screen 0 resolution:  1920x1080
[OpenGL] glDisplay -- X window resolution:    1920x1080
[OpenGL] glDisplay -- display device initialized (1920x1080)
[video]  created glDisplay from display://0
------------------------------------------------
glDisplay video options:
------------------------------------------------
  -- URI: display://0
     - protocol:  display
     - location:  0
  -- deviceType: display
  -- ioType:     output
  -- width:      1920
  -- height:     1080
  -- frameRate:  0
  -- numBuffers: 4
  -- zeroCopy:   true
------------------------------------------------
[TRT]    downloading model Googlenet.tar.gz...
cd networks ; wget --quiet --show-progress --progress=bar:force:noscroll --no-check-certificate https://nvidia.box.com/shared/static/u28j5jm4hnf1ex94dnhsuyu8p799l5d5.gz -O Googlenet.tar.gz ; tar -xzvf Googlenet.tar.gz ; rm Googlenet.tar.gz
Googlenet.tar.gz    100%[===================>]  47,28M  11,1MB/s    in 5,2s    
Googlenet/
Googlenet/bvlc_googlenet.caffemodel
Googlenet/googlenet_noprob.prototxt
Googlenet/googlenet.prototxt
[TRT]    downloaded model Googlenet.tar.gz

imageNet -- loading classification network model from:
         -- prototxt     networks/Googlenet/googlenet.prototxt
         -- model        networks/Googlenet/bvlc_googlenet.caffemodel
         -- class_labels networks/ilsvrc12_synset_words.txt
         -- input_blob   'data'
         -- output_blob  'prob'
         -- batch_size   1

[TRT]    TensorRT version 8.4.1
[TRT]    loading NVIDIA plugins...
[TRT]    Registered plugin creator - ::GridAnchor_TRT version 1
[TRT]    Registered plugin creator - ::GridAnchorRect_TRT version 1
[TRT]    Registered plugin creator - ::NMS_TRT version 1
[TRT]    Registered plugin creator - ::Reorg_TRT version 1
[TRT]    Registered plugin creator - ::Region_TRT version 1
[TRT]    Registered plugin creator - ::Clip_TRT version 1
[TRT]    Registered plugin creator - ::LReLU_TRT version 1
[TRT]    Registered plugin creator - ::PriorBox_TRT version 1
[TRT]    Registered plugin creator - ::Normalize_TRT version 1
[TRT]    Registered plugin creator - ::ScatterND version 1
[TRT]    Registered plugin creator - ::RPROI_TRT version 1
[TRT]    Registered plugin creator - ::BatchedNMS_TRT version 1
[TRT]    Registered plugin creator - ::BatchedNMSDynamic_TRT version 1
[TRT]    Registered plugin creator - ::BatchTilePlugin_TRT version 1
[TRT]    Could not register plugin creator -  ::FlattenConcat_TRT version 1
[TRT]    Registered plugin creator - ::CropAndResize version 1
[TRT]    Registered plugin creator - ::CropAndResizeDynamic version 1
[TRT]    Registered plugin creator - ::DetectionLayer_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_ONNX_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_Explicit_TF_TRT version 1
[TRT]    Registered plugin creator - ::EfficientNMS_Implicit_TF_TRT version 1
[TRT]    Registered plugin creator - ::ProposalDynamic version 1
[TRT]    Registered plugin creator - ::Proposal version 1
[TRT]    Registered plugin creator - ::ProposalLayer_TRT version 1
[TRT]    Registered plugin creator - ::PyramidROIAlign_TRT version 1
[TRT]    Registered plugin creator - ::ResizeNearest_TRT version 1
[TRT]    Registered plugin creator - ::Split version 1
[TRT]    Registered plugin creator - ::SpecialSlice_TRT version 1
[TRT]    Registered plugin creator - ::InstanceNormalization_TRT version 1
[TRT]    Registered plugin creator - ::InstanceNormalization_TRT version 2
[TRT]    Registered plugin creator - ::CoordConvAC version 1
[TRT]    Registered plugin creator - ::DecodeBbox3DPlugin version 1
[TRT]    Registered plugin creator - ::GenerateDetection_TRT version 1
[TRT]    Registered plugin creator - ::MultilevelCropAndResize_TRT version 1
[TRT]    Registered plugin creator - ::MultilevelProposeROI_TRT version 1
[TRT]    Registered plugin creator - ::NMSDynamic_TRT version 1
[TRT]    Registered plugin creator - ::PillarScatterPlugin version 1
[TRT]    Registered plugin creator - ::VoxelGeneratorPlugin version 1
[TRT]    Registered plugin creator - ::MultiscaleDeformableAttnPlugin_TRT version 1
[TRT]    detected model format - caffe  (extension '.caffemodel')
[TRT]    desired precision specified for GPU: FASTEST
[TRT]    requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT]    Unable to determine GPU memory usage
[TRT]    Unable to determine GPU memory usage
[TRT]    [MemUsageChange] Init CUDA: CPU +6, GPU +0, now: CPU 42, GPU 0 (MiB)
[TRT]    CUDA initialization failure with error: 999. Please check your CUDA installation:  http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html
[TRT]    DetectNativePrecisions() failed to create TensorRT IBuilder instance
[TRT]    selecting fastest native precision for GPU:  FP32
[TRT]    could not find engine cache networks/Googlenet/bvlc_googlenet.caffemodel.1.1.8401.GPU.FP32.engine
[TRT]    cache file invalid, profiling network model on device GPU
[TRT]    Unable to determine GPU memory usage
[TRT]    Unable to determine GPU memory usage
[TRT]    [MemUsageChange] Init CUDA: CPU +2, GPU +0, now: CPU 45, GPU 0 (MiB)
[TRT]    CUDA initialization failure with error: 999. Please check your CUDA installation:  http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html
Segmentation fault (core dumped)

i’ll try reflashing the card with jetpack 5.1.1
is possible that the carrier board ( A205 ) drivers flashed with the Jetpack give problems with the CUDA drivers ? i’m following this guide : A205 Carrier Board | Seeed Studio Wiki

OK, I’m not sure about flashing the other carrier board, sorry about that @eracle94. I would also recommend running the trtexec tool on a model (it’s found under /usr/src/tensorrt/bin) to see if TensorRT is able to run at all, or if this issue is particular to jetson-inference.

i tried to install jetpack 5.1.1 but it failed to install , i don’t know why . i will try again with jetpack 5.0.2 . after the installation i will try running the tensorrt. If this doesn’t work , how am i suppose to use this board ?

What I would do, is first make sure you are able to get your board flashed and setup correctly - if needed, contact the carrier board vendor or file a new topic about the problem you had flashing JetPack 5.1.1.

Then once you get JetPack flashed okay, start trying CUDA samples and TensorRT samples to make sure that they run okay:

cd /usr/local/cuda/samples/1_Utilities/deviceQuery
sudo make
./deviceQuery

“”"
OK, I’m not sure about flashing the other carrier board, sorry about that @eracle94. I would also recommend running the trtexec tool on a model (it’s found under /usr/src/tensorrt/bin) to see if TensorRT is able to run at all, or if this issue is particular to jetson-inference.
“”"

Hi , i’ve tried both your suggestion ( with the jetpack 5.0.2 for now ) and their output is respectively ( they seem to work ) :

jetson-poc@ubuntu:/usr/src/tensorrt/bin$ ./trtexec 
&&&& RUNNING TensorRT.trtexec [TensorRT v8401] # ./trtexec
=== Model Options ===
  --uff=<file>                UFF model
  --onnx=<file>               ONNX model
  --model=<file>              Caffe model (default = no model, random weights used)
  --deploy=<file>             Caffe prototxt file
  --output=<name>[,<name>]*   Output names (it can be specified multiple times); at least one output is required for UFF and Caffe
  --uffInput=<name>,X,Y,Z     Input blob name and its dimensions (X,Y,Z=C,H,W), it can be specified multiple times; at least one is required for UFF models
  --uffNHWC                   Set if inputs are in the NHWC layout instead of NCHW (use X,Y,Z=H,W,C order in --uffInput)

=== Build Options ===
  --maxBatch                  Set max batch size and build an implicit batch engine (default = same size as --batch)
                              This option should not be used when the input model is ONNX or when dynamic shapes are provided.
  --minShapes=spec            Build with dynamic shapes using a profile with the min shapes provided
  --optShapes=spec            Build with dynamic shapes using a profile with the opt shapes provided
  --maxShapes=spec            Build with dynamic shapes using a profile with the max shapes provided
  --minShapesCalib=spec       Calibrate with dynamic shapes using a profile with the min shapes provided
  --optShapesCalib=spec       Calibrate with dynamic shapes using a profile with the opt shapes provided
  --maxShapesCalib=spec       Calibrate with dynamic shapes using a profile with the max shapes provided
                              Note: All three of min, opt and max shapes must be supplied.
                                    However, if only opt shapes is supplied then it will be expanded so
                                    that min shapes and max shapes are set to the same values as opt shapes.
                                    Input names can be wrapped with escaped single quotes (ex: \'Input:0\').
                              Example input shapes spec: input0:1x3x256x256,input1:1x3x128x128
                              Each input shape is supplied as a key-value pair where key is the input name and
                              value is the dimensions (including the batch dimension) to be used for that input.
                              Each key-value pair has the key and value separated using a colon (:).
                              Multiple input shapes can be provided via comma-separated key-value pairs.
  --inputIOFormats=spec       Type and format of each of the input tensors (default = all inputs in fp32:chw)
                              See --outputIOFormats help for the grammar of type and format list.
                              Note: If this option is specified, please set comma-separated types and formats for all
                                    inputs following the same order as network inputs ID (even if only one input
                                    needs specifying IO format) or set the type and format once for broadcasting.
  --outputIOFormats=spec      Type and format of each of the output tensors (default = all outputs in fp32:chw)
                              Note: If this option is specified, please set comma-separated types and formats for all
                                    outputs following the same order as network outputs ID (even if only one output
                                    needs specifying IO format) or set the type and format once for broadcasting.
                              IO Formats: spec  ::= IOfmt[","spec]
                                          IOfmt ::= type:fmt
                                          type  ::= "fp32"|"fp16"|"int32"|"int8"
                                          fmt   ::= ("chw"|"chw2"|"chw4"|"hwc8"|"chw16"|"chw32"|"dhwc8"|
                                                     "cdhw32"|"hwc"|"dla_linear"|"dla_hwc4")["+"fmt]
  --workspace=N               Set workspace size in MiB.
  --memPoolSize=poolspec      Specify the size constraints of the designated memory pool(s) in MiB.
                              Note: Also accepts decimal sizes, e.g. 0.25MiB. Will be rounded down to the nearest integer bytes.
                              Pool constraint: poolspec ::= poolfmt[","poolspec]
                                               poolfmt ::= pool:sizeInMiB
                                               pool ::= "workspace"|"dlaSRAM"|"dlaLocalDRAM"|"dlaGlobalDRAM"
  --profilingVerbosity=mode   Specify profiling verbosity. mode ::= layer_names_only|detailed|none (default = layer_names_only)
  --minTiming=M               Set the minimum number of iterations used in kernel selection (default = 1)
  --avgTiming=M               Set the number of times averaged in each iteration for kernel selection (default = 8)
  --refit                     Mark the engine as refittable. This will allow the inspection of refittable layers 
                              and weights within the engine.
  --sparsity=spec             Control sparsity (default = disabled). 
                              Sparsity: spec ::= "disable", "enable", "force"
                              Note: Description about each of these options is as below
                                    disable = do not enable sparse tactics in the builder (this is the default)
                                    enable  = enable sparse tactics in the builder (but these tactics will only be
                                              considered if the weights have the right sparsity pattern)
                                    force   = enable sparse tactics in the builder and force-overwrite the weights to have
                                              a sparsity pattern (even if you loaded a model yourself)
  --noTF32                    Disable tf32 precision (default is to enable tf32, in addition to fp32)
  --fp16                      Enable fp16 precision, in addition to fp32 (default = disabled)
  --int8                      Enable int8 precision, in addition to fp32 (default = disabled)
  --best                      Enable all precisions to achieve the best performance (default = disabled)
  --directIO                  Avoid reformatting at network boundaries. (default = disabled)
  --precisionConstraints=spec Control precision constraint setting. (default = none)
                                  Precision Constaints: spec ::= "none" | "obey" | "prefer"
                                  none = no constraints
                                  prefer = meet precision constraints set by --layerPrecisions/--layerOutputTypes if possible
                                  obey = meet precision constraints set by --layerPrecisions/--layerOutputTypes or fail
                                         otherwise
  --layerPrecisions=spec      Control per-layer precision constraints. Effective only when precisionConstraints is set to
                              "obey" or "prefer". (default = none)
                              The specs are read left-to-right, and later ones override earlier ones. "*" can be used as a
                              layerName to specify the default precision for all the unspecified layers.
                              Per-layer precision spec ::= layerPrecision[","spec]
                                                  layerPrecision ::= layerName":"precision
                                                  precision ::= "fp32"|"fp16"|"int32"|"int8"
  --layerOutputTypes=spec     Control per-layer output type constraints. Effective only when precisionConstraints is set to
                              "obey" or "prefer". (default = none)
                              The specs are read left-to-right, and later ones override earlier ones. "*" can be used as a
                              layerName to specify the default precision for all the unspecified layers. If a layer has more than
                              one output, then multiple types separated by "+" can be provided for this layer.
                              Per-layer output type spec ::= layerOutputTypes[","spec]
                                                    layerOutputTypes ::= layerName":"type
                                                    type ::= "fp32"|"fp16"|"int32"|"int8"["+"type]
  --calib=<file>              Read INT8 calibration cache file
  --safe                      Enable build safety certified engine
  --consistency               Perform consistency checking on safety certified engine
  --restricted                Enable safety scope checking with kSAFETY_SCOPE build flag
  --saveEngine=<file>         Save the serialized engine
  --loadEngine=<file>         Load a serialized engine
  --tacticSources=tactics     Specify the tactics to be used by adding (+) or removing (-) tactics from the default 
                              tactic sources (default = all available tactics).
                              Note: Currently only cuDNN, cuBLAS, cuBLAS-LT, and edge mask convolutions are listed as optional
                                    tactics.
                              Tactic Sources: tactics ::= [","tactic]
                                              tactic  ::= (+|-)lib
                                              lib     ::= "CUBLAS"|"CUBLAS_LT"|"CUDNN"|"EDGE_MASK_CONVOLUTIONS"
                              For example, to disable cudnn and enable cublas: --tacticSources=-CUDNN,+CUBLAS
  --noBuilderCache            Disable timing cache in builder (default is to enable timing cache)
  --timingCacheFile=<file>    Save/load the serialized global timing cache

=== Inference Options ===
  --batch=N                   Set batch size for implicit batch engines (default = 1)
                              This option should not be used when the engine is built from an ONNX model or when dynamic
                              shapes are provided when the engine is built.
  --shapes=spec               Set input shapes for dynamic shapes inference inputs.
                              Note: Input names can be wrapped with escaped single quotes (ex: \'Input:0\').
                              Example input shapes spec: input0:1x3x256x256, input1:1x3x128x128
                              Each input shape is supplied as a key-value pair where key is the input name and
                              value is the dimensions (including the batch dimension) to be used for that input.
                              Each key-value pair has the key and value separated using a colon (:).
                              Multiple input shapes can be provided via comma-separated key-value pairs.
  --loadInputs=spec           Load input values from files (default = generate random inputs). Input names can be wrapped with single quotes (ex: 'Input:0')
                              Input values spec ::= Ival[","spec]
                                           Ival ::= name":"file
  --iterations=N              Run at least N inference iterations (default = 10)
  --warmUp=N                  Run for N milliseconds to warmup before measuring performance (default = 200)
  --duration=N                Run performance measurements for at least N seconds wallclock time (default = 3)
  --sleepTime=N               Delay inference start with a gap of N milliseconds between launch and compute (default = 0)
  --idleTime=N                Sleep N milliseconds between two continuous iterations(default = 0)
  --streams=N                 Instantiate N engines to use concurrently (default = 1)
  --exposeDMA                 Serialize DMA transfers to and from device (default = disabled).
  --noDataTransfers           Disable DMA transfers to and from device (default = enabled).
  --useManagedMemory          Use managed memory instead of separate host and device allocations (default = disabled).
  --useSpinWait               Actively synchronize on GPU events. This option may decrease synchronization time but increase CPU usage and power (default = disabled)
  --threads                   Enable multithreading to drive engines with independent threads or speed up refitting (default = disabled) 
  --useCudaGraph              Use CUDA graph to capture engine execution and then launch inference (default = disabled).
                              This flag may be ignored if the graph capture fails.
  --timeDeserialize           Time the amount of time it takes to deserialize the network and exit.
  --timeRefit                 Time the amount of time it takes to refit the engine before inference.
  --separateProfileRun        Do not attach the profiler in the benchmark run; if profiling is enabled, a second profile run will be executed (default = disabled)
  --buildOnly                 Exit after the engine has been built and skip inference perf measurement (default = disabled)

=== Build and Inference Batch Options ===
                              When using implicit batch, the max batch size of the engine, if not given, 
                              is set to the inference batch size;
                              when using explicit batch, if shapes are specified only for inference, they 
                              will be used also as min/opt/max in the build profile; if shapes are 
                              specified only for the build, the opt shapes will be used also for inference;
                              if both are specified, they must be compatible; and if explicit batch is 
                              enabled but neither is specified, the model must provide complete static
                              dimensions, including batch size, for all inputs
                              Using ONNX models automatically forces explicit batch.

=== Reporting Options ===
  --verbose                   Use verbose logging (default = false)
  --avgRuns=N                 Report performance measurements averaged over N consecutive iterations (default = 10)
  --percentile=P              Report performance for the P percentage (0<=P<=100, 0 representing max perf, and 100 representing min perf; (default = 99%)
  --dumpRefit                 Print the refittable layers and weights from a refittable engine
  --dumpOutput                Print the output tensor(s) of the last inference iteration (default = disabled)
  --dumpProfile               Print profile information per layer (default = disabled)
  --dumpLayerInfo             Print layer information of the engine to console (default = disabled)
  --exportTimes=<file>        Write the timing results in a json file (default = disabled)
  --exportOutput=<file>       Write the output tensors to a json file (default = disabled)
  --exportProfile=<file>      Write the profile information per layer in a json file (default = disabled)
  --exportLayerInfo=<file>    Write the layer information of the engine in a json file (default = disabled)

=== System Options ===
  --device=N                  Select cuda device N (default = 0)
  --useDLACore=N              Select DLA core N for layers that support DLA (default = none)
  --allowGPUFallback          When DLA is enabled, allow GPU fallback for unsupported layers (default = disabled)
  --plugins                   Plugin library (.so) to load (can be specified multiple times)

=== Help ===
  --help, -h                  Print this message
&&&& PASSED TensorRT.trtexec [TensorRT v8401] # ./trtexec

the second suggestion :

jetson-poc@ubuntu:/usr/local/cuda/samples/1_Utilities/deviceQuery$ ./deviceQuery 
./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "Xavier"
  CUDA Driver Version / Runtime Version          11.4 / 11.4
  CUDA Capability Major/Minor version number:    7.2
  Total amount of global memory:                 6846 MBytes (7178903552 bytes)
  (006) Multiprocessors, (064) CUDA Cores/MP:    384 CUDA Cores
  GPU Max Clock rate:                            1109 MHz (1.11 GHz)
  Memory Clock rate:                             1109 Mhz
  Memory Bus Width:                              256-bit
  L2 Cache Size:                                 524288 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total shared memory per multiprocessor:        98304 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 1 copy engine(s)
  Run time limit on kernels:                     No
  Integrated GPU sharing Host Memory:            Yes
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Managed Memory:                Yes
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 0 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.4, CUDA Runtime Version = 11.4, NumDevs = 1
Result = PASS