Google Coral DEV Board Mini Google Coral Dev Board Mini 2 GB 4 x 1.5 GHz

The Google Coral Dev Board Mini is a low-cost single-board computer (SBC) with built-in real-time inference module and an EdgeTPU (Tensor Processing Unit) for powerful machine learning / deep learning algorithms.

The developer board integrates a MediaTek 8167 SoC with the Edge TPU. In contrast to the Coral USB Accelerator, it thus represents a stand-alone platform on which you can run your application completely.
With the Edge TPU, Tensor Flow Lite models can be used quickly and energy-saving for inference. A particular advantage of this solution is that your data remains local. This helps with latency and, of course, data protection in accordance with the basic data protection regulation (GDPR).

Google is increasingly using artificial intelligence (AI) and machine learning (ML) to realize its services. To do this, it developed specialized processors called TPU ("tensor processing Unit") for its data centers, which can execute the algorithms faster and more energy-saving with the TensorFlow Framework. For example, Google Maps is enhanced by street-view street signs that are analyzed using a TensorFlow-based neural network. The clou: TensorFlow can be easily programd in Python.

The Edge TPU supports the TensorFlow Lite framework and can perform up to 4 trillion operations per second with only 2 W consumption. TensorFlow Lite is a modified version of TensorFlow that has been specially adapted to the needs of mobile devices and embedded devices. Many tensorFlow applications can also be implemented in TensorFlow Lite.

This text is machine translated.