NVIDIA JetPack SDK is the most comprehensive solution for building AI applications. Use NVIDIA SDK Manager to flash your Jetson developer kit with the latest OS image, install developer tools for both host computer and developer kit, and install the libraries and APIs, samples, and documentation needed to jumpstart your development environment.

JetPack 4.2.1

JetPack 4.2.1 is the latest production release supporting Jetson AGX Xavier, Jetson TX2 series modules, Jetson TX1, and Jetson Nano. In addition to new features listed below, this release also introduces two beta features: NVIDIA Container Runtime with Docker integration and TensorRT support for INT-8 DLA operations.

Installing JetPack:

Jetson Nano Developer Kit

Download the Jetson Nano Developer Kit SD Card image.

Follow the steps at Getting Started with Jetson Nano Developer Kit.

Jetson AGX Xavier, Jetson TX2 series, Jetson TX1, and Jetson Nano

Download the NVIDIA SDK Manager.

Follow the steps at Install Jetson Software with SDK Manager.

Key Features in JetPack

JetPack includes OS images, Libraries and APIs, developer tools, samples, and documentation.

For more detail about the following JetPack components and features, see the JetPack Release Notes.

OS

NVIDIA L4T provides the bootloader, Linux kernel, necessary firmwares, NVIDIA drivers, sample filesystem, and more.

JetPack 4.2.1 Highlights:

  • Supports two new Jetson modules:
    • Jetson TX2 4GB (P3489-0080)
    • Jetson Nano (P3448-0020)
  • New features for all Jetson products
    • NVIDIA Indicator Applet
      • Enables switching between nvpmodel profiles; monitors and alerts any voltage drop events.
    • Supports headless initial configuration
      • Developer kits support initial configuration from another computer connected via the same USB port used for flashing. This is an alternative to setup with display, keyboard, and mouse attached to developer kit.
    • Supports DeepStream 4.0
    • Supports ISAAC version 2019.2
  • New for Jetson AGX Xavier and Jetson TX2 series modules
    • Supports FreeRTOS for SPE (Cortex-R5)
      • Enables open source real-time operating system to run on the Sensor Processing Engine (SPE) in Jetson AGX Xavier and Jetson TX2 series modules. Example use cases include sensor data processing, wake up management, UAV, and robotics applications.
    • Trusty, a Trusted Execution Environment that enables booting a Trusted OS
      • Provides a framework for customers to use when implementing applications that work with confidential assets.
  • New for Jetson Nano
    • Improved memory availability
      • Reduced memory consumption and improved low-memory handling via use of ZRAM and system software optimizations.
    • Better handling of insufficient power supplies
      • Boot process updated to require less power
    • Secure boot now supported on Jetson Nano (already supported on Jetson AGX Xavier and Jetson TX2 series modules)
      • Secure boot provides a cryptographic checks at each stage of the boot process. These checks ensure the integrity of the software component to prevent unauthorized code from being run.

TensorRT

TensorRT is a high performance deep learning inference runtime for image classification, segmentation, and object detection neural networks. It speeds up deep learning inference as well as reducing the runtime memory footprint for convolutional and deconv neural networks.

JetPack 4.2.1 Highlights:

  • New and updated layers
  • Two new Python samples
  • Updated Parser with support for many new ops
  • New engine refitter
    • TensorRT engines can now be dynamically refitted with new weights without rebuilding the entire engine.
  • Updated Parser with support for many new ops
  • Improved performance/watt for IMMA and HMMA kernels
    • The efficiency has been improved for both FP16 and INT8 modes across the platforms.

cuDNN

CUDA Deep Neural Network library provides high-performance primitives for deep learning frameworks. It includes support for convolutions, activation functions and tensor transformations.

JetPack 4.2.1 Highlights:

  • Many new and enhanced APIs, functions, algorithms, and datatypes.

CUDA

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 4.2.1 Highlights:

  • NVCC adds support for GCC 7.3

Multimedia API

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.

Computer Vision

VisionWorks is a software development package for Computer Vision (CV) and image processing.

OpenCV is the leading open source library for computer vision, image processing and machine learning, and now features GPU acceleration for real-time operation.

Developer Tools

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 4.2.1 Highlights:

  • NVIDIA Nsight Systems
    • Timeline improvements to quickly show more or less information.
  • NVIDIA Nsight Graphics
    • Adds OpenGL and Vulkan Interoperability debugging
    • Adds new configurable range profiler as default option. (The legacy range profiler will be deprecated in a future version.)

For a full list of samples and documentation, see the JetPack documentation.

For older versions of JetPack, please visit the JetPack Archive.