This file has been truncated. show original
<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
<p align="right"><sup><a href="jetpack-setup-2.md">Back</a> | <a href="imagenet-console-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
# Building the Project from Source
Provided with the repo is a library of TensorRT-accelerated deep learning networks for image recognition, object detection with localization (i.e. bounding boxes), and semantic segmentation. This inferencing library (`libjetson-inference`) is intended to be built & run on the Jetson, and includes support for both C++ and Python.
Various pre-trained DNN models are automatically downloaded to get you up and running quickly. It's also setup to accept customized models that you may have trained yourself, including support for Caffe, TensorFlow UFF, and ONNX.
The latest source can be obtained from [GitHub](http://github.com/dusty-nv/jetson-inference) and compiled onboard Jetson Nano, Jetson TX1/TX2, and Jetson AGX Xavier once they have been [flashed with JetPack](jetpack-setup-2.md) or setup with the pre-populated [SD card image](https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit#write) for Jetson Nano.
### Quick Reference
Here's a condensed form of the commands to download, build, and install the project:
$ sudo apt-get update
$ sudo apt-get install git cmake libpython3-dev python3-numpy