This page contains instructions for installing various open-source software packages and frameworks on NVIDIA Jetson, including a collection of DNN models.
Below are links to pre-compiled binaries for Jetson's aarch64 (arm64) architecture, including support for CUDA where applicable. These are intended to be installed on top of JetPack.
Jetson is able to natively run the full versions of popular machine learning frameworks, including TensorFlow, PyTorch, Caffe2, Keras, and MXNet.
There are also helpful deep learning examples and tutorials available, created specifically for Jetson - like Hello AI World.
- Website: https://tensorflow.org
- Source: https://github.com/tensorflow/tensorflow
- Version: TensorFlow 1.13.1
- Packages: pip wheel (Python 3.6)
- Supports: JetPack 4.2 (Jetson Nano / TX2 / Xavier)
- Procedure: docs.nvidia.com/deeplearning/frameworks/install-tf-xavier/index.html#prereqs
- Forum Topic: devtalk.nvidia.com/default/topic/1048776/jetson-nano/official-tensorflow-for-jetson-nano-/
# install prerequisites $ sudo apt-get install libhdf5-serial-dev hdf5-tools libhdf5-dev python3-pip $ pip3 install --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v42 tensorflow-gpu==1.13.1+nv19.5 --user
- Website: https://pytorch.org/
- Source: https://github.com/pytorch/pytorch
- Version: PyTorch v1.0.0 / v1.1.0
|Python 2.7||Python 3.6|
|v1.0.0||pip wheel||pip wheel|
|v1.1.0||pip wheel||pip wheel|
- Support: JetPack 4.2 (Jetson Nano / TX2 / Xavier)
- Forum Topic: devtalk.nvidia.com/default/topic/1049071/jetson-nano/pytorch-for-jetson-nano/
note — the PyTorch and Caffe2 projects have merged, so installing PyTorch will also install Caffe2
# Python 2.7 $ pip install torch-1.1.0-cp27-cp27mu-linux_aarch64.whl # Python 3.6 $ pip3 install numpy torch-1.1.0-cp36-cp36m-linux_aarch64.whl
Hello AI World
IoT / Edge
Listed below are various DNN models that are known to run on Jetson, along with TensorRT for accelerated inferencing.