Jetpack 4.5 Archive
NVIDIA JetPack SDK is the most comprehensive solution for building AI applications. All Jetson modules and developer kits are supported by JetPack SDK.
JetPack SDK includes the latest Linux Driver Package (L4T) with Linux operating system and CUDA-X accelerated libraries and APIs for Deep Learning, Computer Vision, Accelerated Computing and Multimedia. It also includes samples, documentation, and developer tools for both host computer and developer kit, and supports higher level SDKs such as DeepStream for streaming video analytics and Isaac for robotics.
JetPack 4.5 is the latest production release, supporting all Jetson modules
Key features include VPI 1.0, Docker 19.03, Security features including enhanced secure boot and support for full disk encryption, enhanced bootloader functionality and a new way of flashing Jetson devices using NFS.
See Highlights below under different sections for a summary of new features enabled with this release, and view the JetPack release notes for more details.
SD Card Image Method
SD Card Image Method
Jetson Nano Developer Kits
For Jetson Nano Developer Kit
Follow the steps at Getting Started with Jetson Nano Developer Kit.
For Jetson Nano 2GB Developer Kit:
Follow the steps at Getting Started with Jetson Nano 2GB Developer Kit.
NVIDIA SDK Manager method
For any Jetson Developer Kit
Follow the steps at Install Jetson Software with SDK Manager.
JetPack can also be installed or upgraded using a Debian package management tool on Jetson. We also host Debian packages for JetPack components for installing on host. Refer to the JetPack documentation for instructions.
Key Features in JetPack
NVIDIA L4T provides the bootloader, Linux kernel, necessary firmwares, NVIDIA drivers, sample filesystem, and more.
JetPack 4.5 includes L4T 32.5 with these highlights:
All Jetson Nano Developer Kits will now show a warning screen if no microSD Card is inserted. It will attempt to boot from other supported media after showing this warning screen.
TensorRT is a high performance deep learning inference runtime for image classification, segmentation, and object detection neural networks. TensorRT is built on CUDA, NVIDIA’s parallel programming model, and enables you to optimize inference for all deep learning frameworks. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.
JetPack 4.5 includes TensorRT 7.1.3
CUDA Deep Neural Network library provides high-performance primitives for deep learning frameworks. It provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.
JetPack 4.5 includes cuDNN 10.2
CUDA Toolkit provides a comprehensive development environment for C and C++ developers building GPU-accelerated applications. The toolkit includes a compiler for NVIDIA GPUs, math libraries, and tools for debugging and optimizing the performance of your applications.
JetPack 4.4.1 and JetPack 4.4 include CUDA 10.2 with these highlights:
The Jetson Multimedia API package provides low level APIs for flexible application development.
Camera application API: libargus offers a low-level frame-synchronous API for camera applications, with per frame camera parameter control, multiple (including synchronized) camera support, and EGL stream outputs. RAW output CSI cameras needing ISP can be used with either libargus or GStreamer plugin. In either case, the V4L2 media-controller sensor driver API is used.
Sensor driver API: V4L2 API enables video decode, encode, format conversion and scaling functionality. V4L2 for encode opens up many features like bit rate control, quality presets, low latency encode, temporal tradeoff, motion vector maps, and more.JetPack 4.5 highlights:
VisionWorks is a software development package for Computer Vision (CV) and image processing.
OpenCV is a leading open source library for computer vision, image processing and machine learning.
VPI (Vision Programing Interface)1, a software library that provides Computer Vision / Image Processing algorithms implemented on PVA2 (Programmable Vision Accelerator), GPU and CPU
JetPack 4.5 includes VPI 1.0 with these highlights:
JetPack 4.5 includes OpenCV 4.1.1
Jetpack 4.5 includes Visionworks 1.61PVA is available only on Jetson AGX Xavier series and Jetson Xavier NX
CUDA Toolkit provides a comprehensive development environment for C and C++ developers building high-performance GPU-accelerated applications with CUDA libraries. The toolkit includes Nsight Eclipse Edition, debugging and profiling tools including Nsight Compute, and a toolchain for cross-compiling applications.
NVIDIA Nsight Systems is a low overhead system-wide profiling tool, providing the insights developers need to analyze and optimize software performance.
NVIDIA Nsight Graphics is a standalone application for debugging and profiling graphics applications.
JetPack 4.5 includes NVIDIA Nsight Systems 2020.5 with these highlights:
JetPack 4.5 includes NVIDIA Nsight Graphics 2020.5 with these highlights:
Refer to release notes for more details.
Supported SDKs and Tools
PowerEstimator is a webapp that simplifies creation of custom power mode profiles and estimates Jetson module power consumption.
JetPack 4.5 supports PowerEstimator
Deepstream SDK is a complete analytics toolkit for AI-based multi-sensor processing and video and audio understanding.
JetPack 4.5 supports DeepStream 5.0 General Availability release
For a full list of samples and documentation, see the JetPack documentation.
For older versions of JetPack, please visit the JetPack Archive.