Skip to content

Nvidia Jetson Orin Nano Super - Libraries Failing #148

Description

@alex-itico

Search before asking

Component

Export, Integrations, Detection

Bug Description

I had problems with CUDA and the libraries, because torch and torchvision for Nvidia Jetson are custom.

When I try to do inference doesnt work, and export fails.

Package Version Editable project location


aiofiles 24.1.0
altair 6.0.0
annotated-doc 0.0.4
annotated-types 0.7.0
anomavision 3.4.0 /home/meterbee_nvidia/Escritorio/anomavision_2
anyio 4.12.1
attrs 25.4.0
blinker 1.9.0
brotli 1.2.0
cachetools 6.2.6
certifi 2026.2.25
charset-normalizer 3.4.4
click 8.3.1
coloredlogs 15.0.1
contourpy 1.3.2
cycler 0.12.1
defusedxml 0.7.1
easydict 1.13
exceptiongroup 1.3.1
fastapi 0.135.1
ffmpy 1.0.0
filelock 3.25.0
flatbuffers 25.12.19
fonttools 4.61.1
fsspec 2026.2.0
gitdb 4.0.12
gitpython 3.1.46
gradio 6.8.0
gradio-client 2.2.0
groovy 0.1.2
h11 0.16.0
hf-gradio 0.4.1
hf-xet 1.3.2
httpcore 1.0.9
httptools 0.8.0
httpx 0.28.1
huggingface-hub 1.5.0
humanfriendly 10.0
idna 3.11
imageio 2.37.2
iniconfig 2.3.0
itsdangerous 2.2.0
jinja2 3.1.6
joblib 1.5.3
jsonschema 4.26.0
jsonschema-specifications 2025.9.1
kiwisolver 1.4.9
lazy-loader 0.4
markdown-it-py 4.0.0
markupsafe 3.0.3
matplotlib 3.8.3
mdurl 0.1.2
ml-dtypes 0.5.4
mpmath 1.3.0
narwhals 2.17.0
networkx 3.1
numpy 1.26.4
onnx 1.20.1
onnx-ir 0.2.0
onnxruntime 1.23.2
onnxscript 0.6.2
opencv-python 4.11.0.86
openvino 2024.6.0
openvino-dev 2024.6.0
openvino-telemetry 2025.2.0
orjson 3.11.7
packaging 26.0
pandas 2.3.3
pillow 12.1.1
pluggy 1.6.0
protobuf 6.33.5
pyarrow 23.0.1
pydantic 2.12.5
pydantic-core 2.41.5
pydeck 0.9.1
pydub 0.25.1
pygments 2.19.2
pyparsing 3.3.2
pytest 8.0.2
python-dateutil 2.9.0.post0
python-multipart 0.0.20
pytz 2025.2
pyyaml 6.0.3
referencing 0.37.0
requests 2.32.5
rich 14.3.3
rpds-py 0.30.0
safehttpx 0.1.7
scikit-image 0.22.0
scikit-learn 1.3.2
scipy 1.15.3
semantic-version 2.10.0
shellingham 1.5.4
six 1.17.0
smmap 5.0.2
starlette 0.52.1
streamlit 1.54.0
sympy 1.14.0
tenacity 9.1.4
threadpoolctl 3.6.0
tifffile 2025.5.10
toml 0.10.2
tomli 2.4.0
tomlkit 0.13.3
torch 2.10.0
torchvision 0.25.0
tornado 6.5.4
tqdm 4.67.3
typer 0.24.1
typing-extensions 4.15.0
typing-inspection 0.4.2
tzdata 2025.3
urllib3 2.6.3
uvicorn 0.41.0
watchdog 6.0.0
websockets 16.0

anomavision_gui_20260625_173223.log

anomavision_20260625_172539.log

Operating System

Ubuntu / Debian / Linux

Python Version

3.10.12

Package Manager Used

uv (e.g., uv pip install)

Target Hardware / Extra Bracket

Custom / Other

Minimal Reproducible Example

anomavision export --config config2.yml
2026-06-25 17:25:39.111885792 [W:onnxruntime:Default, device_discovery.cc:164 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:89 ReadFileContents Failed to open file: "/sys/class/drm/card1/device/vendor"
2026-06-25 17:25:39,312 - anomavision - INFO - Anomavision logging initialized - Level: INFO
2026-06-25 17:25:39,312 - anomavision - INFO - Log file: logs/anomavision_20260625_172539.log
2026-06-25 17:25:39,313 - anomavision.export - INFO - === export start === model=distributions/padim/sellos_v2/sello_perfecto/anomavision_model.pt fmt=engine in_shape=(1, 3, 160, 160) dyn_batch=True opset=18 precision=auto device=cuda opt=False
2026-06-25 17:25:39,313 - anomavision.export - INFO - Auto-detected device: CUDA
2026-06-25 17:25:39,314 - anomavision.export - INFO - === export done in 0.00s ===

Additional Context

Torch and Torchvision libraries are download from:

pip install https://github.com/ultralytics/assets/releases/download/v0.0.0/torch-2.10.0-cp310-cp310-linux_aarch64.whl
pip install https://github.com/ultralytics/assets/releases/download/v0.0.0/torchvision-0.25.0-cp310-cp310-linux_aarch64.whl

Contribution

  • I'm willing to submit a PR to fix this issue

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions