Zum Inhalt springen

WSAL24432 – Jetson Orin Nano/en

Aus JW Tech Wiki

Documentation notice: This technical documentation was independently rewritten from an archived supplier source. Check technical details and commands against the product version and manufacturer documentation before use.

Summary

Technical overview and configuration guide for the NVIDIA Jetson Orin Nano AI development module, including hardware specifications, firmware updates, and AI runtime environment setup.

Related products at JW Tech

Technical overview

  • The module is available in 4 GB and 8 GB LPDDR5 memory versions, delivering up to 20 or 40 TOPS of AI performance.
  • It features a 6-core Arm Cortex-A78AE v8.2 64-bit CPU and a 1024-core NVIDIA Ampere GPU with 16 (for 4 GB) or 32 (for 8 GB) Tensor Cores.
  • The official developer kit is based on the 8 GB module and adds an SD card slot for system installation.
  • To enter recovery mode, short the FC REC and GND pins under the module with jumpers, then connect via a USB data cable to an Ubuntu host.
  • Firmware updates require an Ubuntu 20.04 or 22.04 host; upgrading to the Super version uses a script with Jetpack 6.2 rather than the SDK Manager.
  • Installing TensorFlow and PyTorch requires downloading the corresponding wheel packages from the official download center; Torchvision must match the installed PyTorch version.

Commands and examples – verify before use:  

sudo dpkg -i sdkmanager_1.6.1-8175_amd64.deb
sudo apt --fix-broken install
sudo mkdir orin_nano && cd orin_nano
wget https://developer.nvidia.com/downloads/embedded/l4t/r36_release_v4.3/release/Jetson_Linux_r36.4.3_aarch64.tbz2
wget https://developer.nvidia.com/downloads/embedded/l4t/r36_release_v4.3/release/Tegra_Linux_Sample-Root-Filesystem_r36.4.3_aarch64.tbz2
sudo tar xf Jetson_Linux_r36.4.3_aarch64.tbz2
sudo tar xpf Tegra_Linux_Sample-Root-Filesystem_r36.4.3_aarch64.tbz2 -C Linux_for_Tegra/rootfs/
cd Linux_for_Tegra/ && sudo ./tools/l4t_flash_prerequisites.sh && sudo ./apply_binaries.sh
sudo ./tools/l4t_create_default_user.sh -u jetson -p jetson1 -a
sudo ./tools/kernel_flash/l4t_initrd_flash.sh --external-device nvme0n1p1 -p "-c ./bootloader/generic/cfg/flash_t234_qspi.xml" -c ./tools/kernel_flash/flash_l4t_t234_nvme.xml --showlogs --network usb0 jetson-orin-nano-devkit-super external
sudo apt-get update -y && sudo apt-get install nvidia-jetpack -y
pip3 install tensorflow-2.12.0+nv23.05-cp38-cp38m-linux_aarch64.whl
python3 -c "import tensorflow as tf; print(tf.__version__)"
sudo apt-get install libjpeg-dev zlib1g-dev libpython3-dev libavcodec-dev libavformat-dev libswscale-dev libopenblas-base libopenmpi-dev
sudo pip3 install torch-2.0.0+nv23.05-cp38-cp38-linux_aarch64.whl
python3 -c "import torch; print(torch.__version__); x = torch.rand(5, 3); print(x)"
git clone --branch v0.14.1 https://github.com/pytorch/vision torchvision && cd torchvision && export BUILD_VERSION=0.14.1 && sudo python3 setup.py install

Notes and version constraints

  • Exact firmware and software versions are location- and time-dependent; verify all steps against current NVIDIA documentation before execution.
  • Upgrading to the Super version depends on the availability of the official upgrade by NVIDIA; this may be delayed.
  • Using a virtualization host requires additional configuration steps that are only partially described in the source text.
  • VNC server setup and remote login require manual confirmation of network parameters.
  • Compatibility between JetPack, CUDA, and Python environments must be verified before installation; version conflicts can cause failures.

Source and revision record

  • Jetson Orin Nano - Waveshare Wiki
  • Source revision: 109261
  • Captured: 2026-09-04T04:18:18+00:00
  • SHA-256: 1767eaca488773f8d3772101a7ec573bacc62c62b86aeab7e953226de4f85db1
Abgerufen von „https://wiki.jw-tech.eu/index.php?title=WSAL24432_–_Jetson_Orin_Nano/en&oldid=2907“