Nvidia Jetson Nano: Vision Transformers & Computer Vision: TAM Unable to run on Jetson Nano Developer

natarajnvidia · February 11, 2025, 2:16pm

Unable to run TAM

jetson-containers run $(autotag tam)

TensorRT version: 10.4.0
-- Building container tam:r36.4.3-onnxruntime

DOCKER_BUILDKIT=0 docker build --network=host --tag tam:r36.4.3-onnxruntime \
--file /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime/Dockerfile \
--build-arg BASE_IMAGE=tam:r36.4.3-tensorrt \
--build-arg ONNXRUNTIME_VERSION="1.21.0" \
--build-arg ONNXRUNTIME_BRANCH="v1.21.0" \
--build-arg ONNXRUNTIME_FLAGS="--allow_running_as_root" \
/home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime \
2>&1 | tee /home/nataraj/aidata/jetson-containers/logs/20250211_192940/build/tam_r36.4.3-onnxruntime.txt; exit ${PIPESTATUS[0]}

DEPRECATED: The legacy builder is deprecated and will be removed in a future release.
            BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0
            environment-variable.

Sending build context to Docker daemon  26.11kB
Step 1/5 : ARG BASE_IMAGE
Step 2/5 : FROM ${BASE_IMAGE}
 ---> 03fe53934962
Step 3/5 : ARG ONNXRUNTIME_VERSION     ONNXRUNTIME_BRANCH     ONNXRUNTIME_FLAGS     FORCE_BUILD=off
 ---> Using cache
 ---> 7945bbfa6491
Step 4/5 : COPY install.sh build.sh /tmp/onnxruntime/
 ---> Using cache
 ---> b965393ae9c1
Step 5/5 : RUN /tmp/onnxruntime/install.sh || /tmp/onnxruntime/build.sh
 ---> Running in 99934d55a54a
+ '[' off == on ']'
+ tarpack install onnxruntime-gpu-1.21.0
+ COMMAND=install
+ PACKAGE=onnxruntime-gpu-1.21.0
+ : /usr/local
+ : /tmp/tarpack
+ : '--quiet --show-progress --progress=bar:force:noscroll'
+ mkdir -p /tmp/tarpack/uploads
+ '[' install == install ']'
+ cd /tmp/tarpack
+ wget --quiet --show-progress --progress=bar:force:noscroll https://apt.jetson-ai-lab.dev/jp6/cu126/onnxruntime-gpu-1.21.0.tar.gz
Building onnxruntime 1.21.0 (branch=v1.21.0, flags=--allow_running_as_root)
+ echo 'Building onnxruntime 1.21.0 (branch=v1.21.0, flags=--allow_running_as_root)'
+ pip3 uninstall -y onnxruntime
WARNING: Skipping onnxruntime as it is not installed.
+ git clone https://github.com/microsoft/onnxruntime /opt/onnxruntime
Cloning into '/opt/onnxruntime'...
Updating files: 100% (9106/9106), done.
+ cd /opt/onnxruntime
+ git checkout v1.21.0
error: pathspec 'v1.21.0' did not match any file(s) known to git
The command '/bin/sh -c /tmp/onnxruntime/install.sh || /tmp/onnxruntime/build.sh' returned a non-zero code: 1
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/tag.py", line 58, in <module>
    image = find_container(args.packages[0], prefer_sources=args.prefer, disable_sources=args.disable, user=args.user, quiet=args.quiet)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/container.py", line 537, in find_container
    return build_container('', package) #, simulate=True)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/container.py", line 147, in build_container
    status = subprocess.run(cmd.replace(_NEWLINE_, ' '), executable='/bin/bash', shell=True, check=True)  
  File "/usr/lib/python3.10/subprocess.py", line 526, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command 'DOCKER_BUILDKIT=0 docker build --network=host --tag tam:r36.4.3-onnxruntime --file /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime/Dockerfile --build-arg BASE_IMAGE=tam:r36.4.3-tensorrt --build-arg ONNXRUNTIME_VERSION="1.21.0" --build-arg ONNXRUNTIME_BRANCH="v1.21.0" --build-arg ONNXRUNTIME_FLAGS="--allow_running_as_root" /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime 2>&1 | tee /home/nataraj/aidata/jetson-containers/logs/20250211_192940/build/tam_r36.4.3-onnxruntime.txt; exit ${PIPESTATUS[0]}' returned non-zero exit status 1.
-- Error:  return code 1
V4L2_DEVICES:  --device /dev/video0  --device /dev/video1 
+ docker run --runtime nvidia -it --rm --network host --shm-size=8g --volume /tmp/argus_socket:/tmp/argus_socket --volume /etc/enctune.conf:/etc/enctune.conf --volume /etc/nv_tegra_release:/etc/nv_tegra_release --volume /tmp/nv_jetson_model:/tmp/nv_jetson_model --volume /var/run/dbus:/var/run/dbus --volume /var/run/avahi-daemon/socket:/var/run/avahi-daemon/socket --volume /var/run/docker.sock:/var/run/docker.sock --volume /home/nataraj/aidata/data:/data -v /etc/localtime:/etc/localtime:ro -v /etc/timezone:/etc/timezone:ro --device /dev/snd -e PULSE_SERVER=unix:/run/user/1000/pulse/native -v /run/user/1000/pulse:/run/user/1000/pulse --device /dev/bus/usb --device /dev/video0 --device /dev/video1 --device /dev/i2c-0 --device /dev/i2c-1 --device /dev/i2c-2 --device /dev/i2c-4 --device /dev/i2c-5 --device /dev/i2c-7 --device /dev/i2c-9 --name jetson_container_20250211_193611
"docker run" requires at least 1 argument.
See 'docker run --help'.

Usage:  docker run [OPTIONS] IMAGE [COMMAND] [ARG...]

Create and run a new container from an image

I tried to build it and it’s the same issue jetson-containers build tam

TensorRT version: 10.4.0
-- Building container tam:r36.4.3-onnxruntime

DOCKER_BUILDKIT=0 docker build --network=host --tag tam:r36.4.3-onnxruntime \
--file /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime/Dockerfile \
--build-arg BASE_IMAGE=tam:r36.4.3-tensorrt \
--build-arg ONNXRUNTIME_VERSION="1.21.0" \
--build-arg ONNXRUNTIME_BRANCH="v1.21.0" \
--build-arg ONNXRUNTIME_FLAGS="--allow_running_as_root" \
/home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime \
2>&1 | tee /home/nataraj/aidata/jetson-containers/logs/20250211_192940/build/tam_r36.4.3-onnxruntime.txt; exit ${PIPESTATUS[0]}

DEPRECATED: The legacy builder is deprecated and will be removed in a future release.
            BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0
            environment-variable.

Sending build context to Docker daemon  26.11kB
Step 1/5 : ARG BASE_IMAGE
Step 2/5 : FROM ${BASE_IMAGE}
 ---> 03fe53934962
Step 3/5 : ARG ONNXRUNTIME_VERSION     ONNXRUNTIME_BRANCH     ONNXRUNTIME_FLAGS     FORCE_BUILD=off
 ---> Using cache
 ---> 7945bbfa6491
Step 4/5 : COPY install.sh build.sh /tmp/onnxruntime/
 ---> Using cache
 ---> b965393ae9c1
Step 5/5 : RUN /tmp/onnxruntime/install.sh || /tmp/onnxruntime/build.sh
 ---> Running in 99934d55a54a
+ '[' off == on ']'
+ tarpack install onnxruntime-gpu-1.21.0
+ COMMAND=install
+ PACKAGE=onnxruntime-gpu-1.21.0
+ : /usr/local
+ : /tmp/tarpack
+ : '--quiet --show-progress --progress=bar:force:noscroll'
+ mkdir -p /tmp/tarpack/uploads
+ '[' install == install ']'
+ cd /tmp/tarpack
+ wget --quiet --show-progress --progress=bar:force:noscroll https://apt.jetson-ai-lab.dev/jp6/cu126/onnxruntime-gpu-1.21.0.tar.gz
Building onnxruntime 1.21.0 (branch=v1.21.0, flags=--allow_running_as_root)
+ echo 'Building onnxruntime 1.21.0 (branch=v1.21.0, flags=--allow_running_as_root)'
+ pip3 uninstall -y onnxruntime
WARNING: Skipping onnxruntime as it is not installed.
+ git clone https://github.com/microsoft/onnxruntime /opt/onnxruntime
Cloning into '/opt/onnxruntime'...
Updating files: 100% (9106/9106), done.
+ cd /opt/onnxruntime
+ git checkout v1.21.0
error: pathspec 'v1.21.0' did not match any file(s) known to git
The command '/bin/sh -c /tmp/onnxruntime/install.sh || /tmp/onnxruntime/build.sh' returned a non-zero code: 1
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/tag.py", line 58, in <module>
    image = find_container(args.packages[0], prefer_sources=args.prefer, disable_sources=args.disable, user=args.user, quiet=args.quiet)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/container.py", line 537, in find_container
    return build_container('', package) #, simulate=True)
  File "/home/nataraj/aidata/jetson-containers/jetson_containers/container.py", line 147, in build_container
    status = subprocess.run(cmd.replace(_NEWLINE_, ' '), executable='/bin/bash', shell=True, check=True)  
  File "/usr/lib/python3.10/subprocess.py", line 526, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command 'DOCKER_BUILDKIT=0 docker build --network=host --tag tam:r36.4.3-onnxruntime --file /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime/Dockerfile --build-arg BASE_IMAGE=tam:r36.4.3-tensorrt --build-arg ONNXRUNTIME_VERSION="1.21.0" --build-arg ONNXRUNTIME_BRANCH="v1.21.0" --build-arg ONNXRUNTIME_FLAGS="--allow_running_as_root" /home/nataraj/aidata/jetson-containers/packages/ml/onnxruntime 2>&1 | tee /home/nataraj/aidata/jetson-containers/logs/20250211_192940/build/tam_r36.4.3-onnxruntime.txt; exit ${PIPESTATUS[0]}' returned non-zero exit status 1.
-- Error:  return code 1
V4L2_DEVICES:  --device /dev/video0  --device /dev/video1 
+ docker run --runtime nvidia -it --rm --network host --shm-size=8g --volume /tmp/argus_socket:/tmp/argus_socket --volume /etc/enctune.conf:/etc/enctune.conf --volume /etc/nv_tegra_release:/etc/nv_tegra_release --volume /tmp/nv_jetson_model:/tmp/nv_jetson_model --volume /var/run/dbus:/var/run/dbus --volume /var/run/avahi-daemon/socket:/var/run/avahi-daemon/socket --volume /var/run/docker.sock:/var/run/docker.sock --volume /home/nataraj/aidata/data:/data -v /etc/localtime:/etc/localtime:ro -v /etc/timezone:/etc/timezone:ro --device /dev/snd -e PULSE_SERVER=unix:/run/user/1000/pulse/native -v /run/user/1000/pulse:/run/user/1000/pulse --device /dev/bus/usb --device /dev/video0 --device /dev/video1 --device /dev/i2c-0 --device /dev/i2c-1 --device /dev/i2c-2 --device /dev/i2c-4 --device /dev/i2c-5 --device /dev/i2c-7 --device /dev/i2c-9 --name jetson_container_20250211_193611
"docker run" requires at least 1 argument.
See 'docker run --help'.

Usage:  docker run [OPTIONS] IMAGE [COMMAND] [ARG...]

Create and run a new container from an image

and when i was trying to run the specific version

jetson-containers run dustynv/tam:r35.4.1

jetson-containers run dustynv/tam:r35.4.1
V4L2_DEVICES:  --device /dev/video0  --device /dev/video1 
+ docker run --runtime nvidia -it --rm --network host --shm-size=8g --volume /tmp/argus_socket:/tmp/argus_socket --volume /etc/enctune.conf:/etc/enctune.conf --volume /etc/nv_tegra_release:/etc/nv_tegra_release --volume /tmp/nv_jetson_model:/tmp/nv_jetson_model --volume /var/run/dbus:/var/run/dbus --volume /var/run/avahi-daemon/socket:/var/run/avahi-daemon/socket --volume /var/run/docker.sock:/var/run/docker.sock --volume /home/nataraj/aidata/data:/data -v /etc/localtime:/etc/localtime:ro -v /etc/timezone:/etc/timezone:ro --device /dev/snd -e PULSE_SERVER=unix:/run/user/1000/pulse/native -v /run/user/1000/pulse:/run/user/1000/pulse --device /dev/bus/usb --device /dev/video0 --device /dev/video1 --device /dev/i2c-0 --device /dev/i2c-1 --device /dev/i2c-2 --device /dev/i2c-4 --device /dev/i2c-5 --device /dev/i2c-7 --device /dev/i2c-9 --name jetson_container_20250211_195513 dustynv/tam:r35.4.1
/usr/local/lib/python3.8/dist-packages/gradio_client/documentation.py:102: UserWarning: Could not get documentation group for <class 'gradio.mix.Parallel'>: No known documentation group for module 'gradio.mix'
  warnings.warn(f"Could not get documentation group for {cls}: {exc}")
/usr/local/lib/python3.8/dist-packages/gradio_client/documentation.py:102: UserWarning: Could not get documentation group for <class 'gradio.mix.Series'>: No known documentation group for module 'gradio.mix'
  warnings.warn(f"Could not get documentation group for {cls}: {exc}")
Traceback (most recent call last):
  File "app.py", line 4, in <module>
    import cv2
  File "/usr/local/lib/python3.8/dist-packages/cv2/__init__.py", line 96, in <module>
    bootstrap()
  File "/usr/local/lib/python3.8/dist-packages/cv2/__init__.py", line 86, in bootstrap
    import cv2
ImportError: libffi.so.8: cannot open shared object file: No such file or directory

kayccc · February 12, 2025, 12:03am

Your previous issue are on Orin Nano, but now are on Jetson Nano.
Are you using Jetson Nano or Orin Nano devkit?

natarajnvidia · February 12, 2025, 12:48am

jetson orin nano developer kit

kayccc · February 12, 2025, 1:42am

Moving over to Orin Nano forum.

AastaLLL · February 12, 2025, 4:32am

Hi,

DOCKER_BUILDKIT=0 docker build --network=host --tag tam:r36.4.3-onnxruntime \
...
--build-arg ONNXRUNTIME_VERSION="1.21.0" \
--build-arg ONNXRUNTIME_BRANCH="v1.21.0" \

We have restored the ONNXRuntime version to 1.20.1.
Please make sure you have the change below.

Thanks.

system · March 12, 2025, 2:29am

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

Topic		Replies	Views
Nvidia Jetson Orin Nano Developer Kit : Vision Transfomer: NanoSAM and Computer Vision : Unable to Install nanosam Jetson Orin Nano jetson , jetson-nano , computer-vision	8	33	March 5, 2025
Jetson container package torch2trt on nano orin 8gb Developement kit Jetson Orin Nano containers	2	654	September 6, 2023
Jetson Orin Nano restarts while running building text-generation-webui (Loading exllamav2_ext extension (JIT)...) Jetson Orin Nano containers , generative_ai	10	54	March 12, 2025
Container torch_tensorrt not working Jetson AGX Orin tensorrt , containers	15	70	March 12, 2025
Torch2trt fail when building container from jetson-containers Jetson AGX Orin tensorrt	10	59	February 10, 2025
Libnvdla_compiler.so not found (bis repetita) Jetson AGX Orin tensorrt	6	33	March 13, 2025
NanoVLM Issue on Jetson Orin Nano Jetson Orin Nano generative_ai	9	620	June 6, 2024
Deploy TAO Classification_pyt FAN for Jetson Nano TAO Toolkit tensorrt , jetson-inference , tao , deepstream	15	360	April 8, 2024
Nanoowl example not working Jetson AGX Orin generative_ai	11	454	May 23, 2024
Jetson Container `Nano_llm` version 24.6-r36.2.0 error on Jepack 6.0 DP Jetson Orin NX containers , generative_ai	5	235	July 4, 2024

Nvidia Jetson Nano: Vision Transformers & Computer Vision: TAM Unable to run on Jetson Nano Developer

Related topics