Description The Accelerator Module is a surface-mounted module that includes the Edge TPU and its own power control. It provides accelerated inferencing for TensorFlow Lite models on your custom PCB hardware.

Performs high-speed ML inferencing The Edge TPU is capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 frames per second, in a power efficient manner. See more performance benchmarks.

Supports TensorFlow Lite No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.

Working frequency: 500 MHz supply voltage: 3.1 v to 3.63 v interface type: PCIe, USB low working temperature: - 20 ℃ high temperature: 70 ℃ + size: 15 mm x 10 mm x 1.5 mm humidity sensitive: yes product type: module system on coral accelerator module (surface installation, with edge of TPU) with coral at the edge of the TPU surface-mount accelerator module is a multichip module, design for machine learning models perform reasoning at a high speed.It includes integrated power control on the verge of TPU M1 accelerator, PCIe generation of 2 x1 or USB2 interface connection.Edge of TPU is a small special integrated circuit design, in the form of energy saving accelerated TensorFlow Lite model.It can perform 4 trillion operations per second (4 top), use 2 watts of power (two top per watt).An Edge, for example, TPU can perform at a speed of almost 400 frames per second advanced mobile visual model, such as MobileNet v2.This kind of equipment on the M1 treatment reduced the delay, increases the data privacy, and eliminates the need for continuous Internet connection.Google devices Coral artificial intelligence platform for building intelligent device provides the hardware components and software tools and precompiled model.Edge features Google TPU ML accelerator 4 TOPS (int8) peak performance per watt 2 TOPS integrated power management PCIe second-generation x1 or USB 2.0 interface surface mounted (LGA) module 15.0 mm x 10.0 mm x 1.5 mm mm mm 0.67 grams weight - 40 to + 85 ℃ temperature rohs compliant applications of machine learning model of embedded gateway platform mini computer industry