Coral from Google - Introduction - SoM Overview

From RidgeRun Developer Wiki




Previous: Introduction/Getting Started Index Next: GStreamer





Features

  • Edge TPU System-on-Module (SoM)
   * NXP i.MX 8M SoC (Quad-core Arm Cortex-A53, plus Cortex-M4F)
   * Google Edge TPU ML accelerator coprocessor
   * Cryptographic coprocessor
   * Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5 GHz)
   * Bluetooth 4.2
   * 8 GB eMMC
   * 1 GB LPDDR4
  • USB connections
   * USB Type-C power port (5V DC)
   * USB 3.0 Type-C OTG port
   * USB 3.0 Type-A host port
   * USB 2.0 Micro-B serial console port
  • Audio connections
   * 3.5 mm audio jack (CTIA compliant)
   * Digital PDM microphone (x2)
   * 2.54 mm 4-pin terminal for stereo speakers
  • Video connections
   * HDMI 2.0a (full size)
   * 39-pin FFC connector for MIPI DSI display (4-lane)
   * 24-pin FFC connector for MIPI CSI-2 camera (4-lane)
  • MicroSD card slot
  • Gigabit Ethernet port
  • 40-pin GPIO expansion header
  • Supports Mendel Linux (derivative of Debian)

Download the datasheet here

Performance

Using MobileNet models for face detection the Edge TPU does the inference 70 to 100 times faster than a CPU and frames per second of up to 70 to 100. The table below shows the performance test done to a 64-bit Intel(R) Xeon(R) E5–1650 v4 @ 3.60GHz with and without a Coral USB Accelerator; also with a Quad-core Cortex-A53 @ 1.5GHz embedded system with and without an Edge TPU.

Performance of the Coral board. Image taken from: https://blog.tensorflow.org/2019/03/build-ai-that-works-offline-with-coral.html


Previous: Introduction/Getting Started Index Next: GStreamer