Edge AI/ML Gateway - IG500
The iG500 offers machine learning at the edge. The system is designed based on NVidia TX2 SoM (System on Module). Jetson TX2 is the fastest, most power-efficient embedded AI computing device. This 7.5-watt supercomputer on a module brings true AI computing at the edge. It’s built around an NVIDIA Pascal™ family GPU and loaded with 8 GB of memory and 59.7 GB/s of memory bandwidth.
Edge AI/ML
Gateway—IG500
Gateway—IG500
Menu
The iG500 offers machine learning at the edge. The system is designed based on NVidia TX2 SoM (System on Module). Jetson TX2 is the fastest, most power-efficient embedded AI computing device. This 7.5-watt supercomputer on a module brings true AI computing at the edge. It’s built around an NVIDIA Pascal™ family GPU and loaded with 8 GB of memory and 59.7 GB/s of memory bandwidth.
iG500 ingest signals from cameras, LIDARs, ultrasonic, RF or analog to digital converters. It then decode and apply machine learning algorithm such as Caffe, Torch, TensorRT or TensorFlow. After completing machine learning algorithm, it displays the image processing or provide signal to an actuator or connect to other systems. It fits perfectly within NybSys IoT product portfolio.
It can be used in mass public transit system, farming and agriculture system, smart city and traffic control system. In manufacturing it can be used for industrial automation and manufacturing flow control. In retail and warehousing it can help in theft detection, object classification and movement detection.
Play Video
iG500 offers unique opportunities to apply already trained models at the edge to perform inference at the edge. It can be used for Image recognition and classification, objection and localization, segmentation and free space visualization, complex event processing. The iG500 have industrial standard DIN rail enclosure with 6 Port ethernet switch for connecting sensors and cameras and 2 SFP module for uplinks. Failover DC power supply units are provided for high availability.
Technical specifications
CPU
ARM Cortex-A57 (quad-core) @ 2GHz + NVIDIA Denver2 (dual-core) @ 2GHz
GPU
256-core Pascal @ 1300MHz
Memory
8GB 128-bit LPDDR4 @ 1866Mhz | 59.7 GB/s
Storage
32GB eMMC 5.1
Encoder
4Kp60, (3x) 4Kp30, (8x) 1080p30
Decoder
(2x) 4Kp60
Display
2x HDMI 2.0 / DP 1.2 / eDP 1.2 | 2x MIPI DSI
Wireless
802.11a/b/g/n/ac 2×2 867Mbps | Bluetooth 4.1
Ethernet
6 port 10/100/1000 BASE-T Ethernet and 2 Fiber optic option
USB
USB 3.0 + USB 2.0
CAN
Dual CAN bus controller
RS 485
High speed serial port for connecting RS 485 compliant sensors
Thermals
-25°C to 80°C
Power
10.5W
Resources
Datasheet