Google Coral M.2 Accelerator with Dual Edge TPU

The Coral M.2 accelerator with dual edge TPU integrates two edge TPUs into existing computer systems with the help of an M.2 E-key interface. This makes this Edge TPU module particularly suitable for mobile and embedded systems that can benefit from accelerated machine learning. Each Edge TPU coprocessor is capable of performing 4 trillion computing operations per second (4 TOPS) with 2 watts of power consumption. For example, modern mobile vision models such as MobileNet v2 can be run efficiently at almost 400 FPS. With two Edge TPUs (and therefore 8 TOPS), you can double the performance of the system - by running two models in parallel, or distributing the processing steps of a model to both Edge TPUs. The M.2 Accelerator with Dual Edge TPU is supported under Debian-Linux based systems, as well as on Windows 10. Technical data Coral M.2 Accelerator with Dual Edge TPU 2 x Google Edge TPU ML accelerator coprocessor 8 TOPS (int8); 2 TOPS per Watt interface and software support interface: M.2 E-key (with two PCIe Gen2 x1 lanes). Supports Linux, and Windows 10 on the host system. Other data dimensions: 22 mm x 30 mm x 2.8 mm (M.2-2230-D3-E) Weight: 2.5 g. Operating temperature: -40 to +85 °C. Requirements for the Linux host system: 64-bit Linux Debian 10.0 / Ubuntu 16.04 (or newer) CPU architecture: x86-64, or ARMv8 (64-bit) or Windows: Windows 10 (64-bit), x86-64 CPU architecture. Important notes: Although the M.2 specification requires E-key sockets to provide two times PCIe x1 Lane, most manufacturers only provide PCIe once! To be able to use both edge TPUs, please make sure your socket actually provides two times PCIe x1.....