Electronicdesign 14289 Ew Tx2 Promo 0
Electronicdesign 14289 Ew Tx2 Promo 0
Electronicdesign 14289 Ew Tx2 Promo 0
Electronicdesign 14289 Ew Tx2 Promo 0
Electronicdesign 14289 Ew Tx2 Promo 0

DNN Popularity Drives NVidia’s Jetson TX2

March 20, 2017
NVidia just released its Jetson TX2, and it’s finding its way into all sorts of platforms.

The increased interest in deep neural nets (DNNs) and deep learning are driving the popularity of platforms like NVidia’s Jetson TX2 (Fig. 1). The 50-mm by 87-mm Jetson TX2 module has a 256-core NVIDIA Pascal GPU, a pair of 64-bit NVIDIA Denver 2 ARM-compatible cores, and four 64-bit ARM A57 cores. It delivers 2 TFLOPs of single precision performance.

The Jetson TX2 supports NVidia’s CUDA programmer environment as well as the cuDNN (CUDA deep neural network) platform, allowing it to support deep-learning frameworks like Caffe and Tensorflow.

1. NVidia’s Jetson TX2 has a 256-core NVIDIA Pascal GPU that delivers 2 TFLOPs of performance.

The Jetson TX2 requires a carrier board to operate. NVidia’s development kit is good for checking out the module, but less so for deployment. Developers need to create their own carrier board or go with one of the many third-party products like Connect Tech’s Orbitty.

Connect Tech has a number of platforms that support the TX1 and TX2, including the 1U Jetson TX2 Array (Fig. 2) rack server that uses 24 modules. The modules are connected using their 1-Gbit Ethernet connections. These are tied together with an on-board switch that has two 10-Gbit and two 1-Gbit SFP+ ports. There is also an on-board, SMARC-based processor that supports three 2.5-in SATA drives and an out-of-band, 1-Gbit Ethernet port. The system has a pair of redundant power supplies.

2. Connect Tech’s Jetson TX2 Array is a 1U rack server that has 24 modules.

Antmicro’s Deep Learning Kit (Fig. 3) supports NVidia’s Jetson TX1 and TX2. It was running Antmicro’s SegNet sequencing neural network that was trained to navigate a model car through city traffic with a propagation time of only 50 ms. The board supports up to 6 CSI-2 cameras.

3. Antmicro’s Deep Learning Kit supports NVidia’s Jetson TX1 and TX2.

For very small systems, developers can use Connect Tech’s Sprocket (Fig. 4). The Sprocket exposes USB OTG and a 4 lane MIPI CSI-2 interface. It also has two 3.3-V UARTs, two I2Cs, and four GPIO pins. The wireless support is built into the Jetson TX1 and TX2, so that’s also available. It is ideal for SWaP-constrained systems such as drones.

4. Connect Tech’s Sprocket supports the Jetson TX1 and TX2.

Sponsored Recommendations

Board-Mount DC/DC Converters in Medical Applications

March 27, 2024
AC/DC or board-mount DC/DC converters provide power for medical devices. This article explains why isolation might be needed and which safety standards apply.

Use Rugged Multiband Antennas to Solve the Mobile Connectivity Challenge

March 27, 2024
Selecting and using antennas for mobile applications requires attention to electrical, mechanical, and environmental characteristics: TE modules can help.

Out-of-the-box Cellular and Wi-Fi connectivity with AWS IoT ExpressLink

March 27, 2024
This demo shows how to enroll LTE-M and Wi-Fi evaluation boards with AWS IoT Core, set up a Connected Health Solution as well as AWS AT commands and AWS IoT ExpressLink security...

How to Quickly Leverage Bluetooth AoA and AoD for Indoor Logistics Tracking

March 27, 2024
Real-time asset tracking is an important aspect of Industry 4.0. Various technologies are available for deploying Real-Time Location.

Comments

To join the conversation, and become an exclusive member of Electronic Design, create an account today!