JETSON XAVIER NX
The World’s Smallest AI Supercomputer for Embedded and Edge Devices
WELCOME TO THE FUTURE OF AUTONOMOUS MACHINES
AI is enabling new applications that were previously considered science fiction—and impacting nearly every industry. Autonomous machines take advantage of AI to solve some of the world’s toughest problems. The NVIDIAⓇ Jetson™ platform gives you the tools to develop and deploy AI-powered robots, drones, IVA applications, and other autonomous machines that think for themselves.
Robotics
Enable robots and other autonomous machines to perceive, navigate, and manipulate the world around them.
Machine Vision
Use AI to quickly identify defects with pinpoint accuracy to ensure the highest product quality with autonomous optical inspection (AOI).
AIoT
Bringing the power of AI to a wide variety of IoT gateways and edge devices, to enable local processing of sensors and data.
Intelligent Video Analytics
Get real-time actionable insights through streaming video analytics.
NVIDIA Jetson Comparison Table
| Jetson Nano | Jetson TX2 Series | Jetson Xavier NX | Jetson AGX Xavier Series | |||||
|---|---|---|---|---|---|---|---|---|
| TX2 4GB | TX2 | TX2i | AGX Xavier 8GB | AGX Xavier | AGX Xavier 32GB | |||
| AI Performance | 472 GFLOPs (0.5 TFLOPs) | 1.33 TFLOPS | 1.26 TFLOPs | 21 TOPs | 20 TOPs | 32 TOPs | ||
| GPU | 128-core NVIDIA Maxwell™ GPU | 256-core NVIDIA Pascal™ GPU | 384-core NVIDIA Volta™ GPU with 48 Tensor Cores | 384-core NVIDIA Volta™ GPU with 48 Tensor Cores | 512-core NVIDIA Volta™ GPU with 64 Tensor Cores | |||
| CPU | Quad-Core ARM® Cortex®-A57 MPCore | Dual-Core NVIDIA Denver 1.5 64-Bit CPU and Quad-Core ARM® Cortex®-A57 MPCore processor | 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3 | 6-core NVIDIA Carmel Arm®v8.2 64-bit CPU 6MB L2 + 4MB L3 | 8-core NVIDIA Carmel Arm®v8.2 64-bit CPU 8MB L2 + 4MB L3 |
|||
| Memory | 4 GB 64-bit LPDDR4 25.6GB/s | 4 GB 128-bit LPDDR4 51.2GB/s | 8 GB 128-bit LPDDR4 59.7GB/s | 8 GB 128-bit LPDDR4 (ECC Support) 51.2GB/s | 8 GB 128-bit LPDDR4x 51.2GB/s | 8 GB 256-bit LPDDR4x 85.3GB/s | 16 GB 256-bit LPDDR4x 136.5GB/s | 32 GB 256-Bit LPDDR4x 137 GB/s |
| Storage | 16 GB eMMC 5.1 (*) | 16 GB eMMC 5.1 | 32 GB eMMC 5.1 | 16 GB eMMC 5.1 | 32 GB eMMC 5.1 | |||
| Power | 5W | 10W | 7.5W | 15W | 10W | 20W | 10W | 15W | 10W | 20W | 10W | 15W | 30W | ||
| PCIe | 1 x4 (PCIe Gen2) | 1 x1 + 1 x4 OR 1 x1 + 1 x1 + 1 x2 (PCIe Gen2) | 1 x1 + 1 x4 (PCIe Gen3, Root Port & Endpoint) | 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen3) | 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen4, Root Port & Endpoint) |
|||
| CSI Camera | Up to 4 cameras 12 lanes MIPI CSI-2 D-PHY 1.1 (up to 18 Gbps) | Up to 6 cameras (12 via virtual channels) 12 lanes MIPI CSI-2 D-PHY 1.2 (up to 30 Gbps) C-PHY 1.1 (up to 41Gbps) | Up to 6 cameras (24 via virtual channels) 14 lanes (3x4 or 6x2) MIPI CSI-2 D-PHY 1.2 (up to 30 Gbps) | Up to 6 cameras (36 via virtual channels) 16 lanes MIPI CSI-2 | 8 lanes SLVS-EC D-PHY 1.2 (up to 40 Gbps) C-PHY 1.1 (up to 91 Gbps) |
||||
| Video Encode | 250MP/sec 1x 4K @ 30 (HEVC) 2x 1080p @ 60 (HEVC) | 500MP/sec 1x 4K @ 60 (HEVC) 3x 4K @ 30 (HEVC) 4x 1080p @ 60 (HEVC) | 2x 464MP/sec 2x 4K @ 30 (HEVC) 6x 1080p @ 60 (HEVC) | 2x 464MP/sec 2x 4K @ 30 (HEVC) 6x 1080p @ 60 (HEVC) 14x 1080p @ 30 (HEVC) | 2x1000MP/sec 4x 4K @ 60 (HEVC) 16x 1080p @ 60 (HEVC) 32x 1080p @ 30 (HEVC) |
|||
| Video Decode | 500 MP/sec 1x 4K @ 60 (HEVC) 4x 1080p @ 60 (HEVC) | 1000 MP/sec 2x 4K @ 60 (HEVC) 7x 1080p @ 60 (HEVC) 20x 1080p @ 30 (HEVC) | 2x690MP/sec 2x 4K @ 60 (HEVC) 12x 1080p @ 60 (HEVC) 32x 1080p @ 30 (HEVC) | 2x690MP/sec 2x 4K @ 60 (HEVC) 12x 1080p @ 60 (HEVC) 32x 1080p @ 30 (HEVC) | 2x1500MP/sec 2x 8K @ 30 (HEVC) 6x 14k @ 60 (HEVC) 26x 1080p @ 60 (HEVC) 72x 1080p @ 30 (HEVC) |
|||
| Display | 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0 1 x2 DSI (1.5Gbps/lane) | 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0 2 x4 DSI (1.5Gbps/lane) | 2 multi-mode DP 1.4/eDP 1.4/HDMI 2.0 No DSI support | 3 multi-mode DP 1.4/eDP 1.4/HDMI 2.0 No DSI support |
||||
| DL Accelerator | — | — | 2x NVDLA Engines | 2x NVDLA Engines | ||||
| Vision Accelerator | — | — | 7-Way VLIW Vision Processor | 7-Way VLIW Vision Processor | ||||
| Networking | Requires external chip for Wi-Fi | Requires external chip for Wi-Fi | Built-in Wi-Fi | Requires external chip for Wi-Fi | Requires external chip for Wi-Fi | Requires external chip for Wi-Fi | ||
| 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet, WLAN | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | |||
| Mechanical | 69.6 mm x 45 mm 260-pin SO-DIMM connector | 87 mm x 50 mm 400-pin connector | 69.6 mm x 45 mm 260-pin SO-DIMM connector | 100 mm x87 mm 699-pin connector |
||||
| * The Jetson Nano module of the Jetson Nano Developer Kit requires an SD-Card for storage. | ||||||||
Jetson Family
Jetson AGX Xavier Series
Jetson AGX Xavier is the first computer designed specifically for autonomous machines. It has six Engines onboard for accelerated sensors data processing and running autonomous machines software, and offers the performance and power efficiency for fully autonomous machines.
Jetson Xavier NX
Jetson Xavier NX brings up to 21 TOPs of accelerated AI computing to the edge in a small form factor module. It can run multiple modern neural networks in parallel and process data from multiple high-resolution sensors—a requirement for full AI systems. Jetson Xavier NX is production-ready and supports all popular AI frameworks.
Jetson TX2 Series
The Jetson TX2 series embedded module for edge AI applications now comes in three versions: Jetson TX2, Jetson TX2i, and the newly available, lower-cost Jetson TX2 4GB. Jetson TX1-based products can migrate to the more powerful Jetson TX2 4GB at the same price.
Jetson TX1
The world’s first supercomputer on a module, Jetson TX1 is capable of delivering the performance and power efficiency needed for the latest visual computing applications. It’s built around the revolutionary NVIDIA Maxwell™ architecture with 256 CUDA cores delivering over 1 TeraFLOPs of performance. 64-bit CPUs, 4K video encode and decode capabilities, and a camera interface capable of 1400 MPix/s make this the best system for embedded deep learning, computer vision, graphics, and GPU computing.
Jetson Nano
The Jetson Nano module is a small AI computer that has the performance and power efficiency needed to run modern AI workloads, multiple neural networks in parallel and process data from several high-resolution sensors simultaneously. This makes it the perfect entry-level option to add advanced AI to embedded products.
Start Developing Your Own AI Applications at the Edge with OpenZeka Trainings
You will learn fundamentals of Deep Learning by training and deploying neural networks. In this course;
– You will learn how to create common AI workflows like Image classification and Object Detection,
– Experiment through various strategies to improve NNs accuracy and performance by tweaking training parameters and NN architectures,
– Deploy your custom NNs to solve real world problems.
This training has been prepared for participants who want to realize real-time image recognition on camera images in autonomous machines, robots, drones and security systems with NVIDIA Jetson TX1 / TX2 / TX2i / Xavier platform.
This course is beneficial for researchers and self-learners who wants to get experienced and do academic research on deep learning applications.
Start developing your own autonomous car software stack with this training!
- Introduction to OpenZeka MARC
- ROS, Git and Control Theory
- OpenCV
- Fundamentals of Deep Learning
- Image Classification and Object Detection
- Sematic Segmentation
- NVIDIA End-to-End Model, Mapping and Localization