Edge TPU Devices

Add accelerated ML to your embedded device

The Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing for low-power devices. For example, it can execute state-of-the-art mobile vision models such as MobileNet V2 at 100+ fps, in a power efficient manner.

With one of the following Edge TPU devices, you can build embedded systems with on-device AI features that are fast, secure, and power efficient.

Edge TPU Dev Board

A single-board computer with a removable Edge TPU system-on-module (SOM).

This all-in-one development board allows you to prototype embedded systems that demand fast ML inferencing. The baseboard provides all the peripheral connections you need, and the SOM board is removable so you can integrate the Edge TPU module into your own hardware.

Coming soon. Get notified.

Edge TPU module (SOM) specifications

CPU NXP i.MX 8M SOC (quad Cortex-A53, Cortex-M4F)
GPU Integrated GC7000 Lite Graphics
ML accelerator Google Edge TPU coprocessor
RAM 1 GB LPDDR4
Flash memory 8 GB eMMC
Wireless Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5GHz)
Bluetooth 4.1
Dimensions 40 mm x 48 mm

Baseboard specifications

Flash memory MicroSD slot
USB Type-C OTG
Type-C power
Type-A 3.0 host
Micro-B serial console
LAN Gigabit Ethernet port
Audio 3.5mm audio jack (CTIA compliant)
Digital PDM microphone (x2)
2.54mm 4-pin terminal for stereo speakers
Video HDMI 2.0a (full size)
39-pin FFC connector for MIPI-DSI display (4-lane)
24-pin FFC connector for MIPI-CSI2 camera (4-lane)
GPIO 40-pin expansion header
Power 5V DC (USB Type-C)
Dimensions 85 mm x 56 mm
Supported Operating Systems

Debian Linux

Supported Frameworks

TensorFlow Lite

Edge TPU Accelerator

A USB device that adds an Edge TPU coprocessor to your system.

This small stick includes a USB Type-C socket that you can connect to any Linux-based system to perform accelerated ML inferencing. The casing includes mounting holes for attachment to host boards.

Coming soon. Get notified.

Specifications

ML accelerator Google Edge TPU coprocessor
Connector USB Type-C* (data/power)
Dimensions 65 mm x 30 mm
* Compatible with Raspberry Pi boards at USB 2.0 speeds only.
Supported Operating Systems

Debian Linux

Supported Frameworks

TensorFlow Lite

Frequently asked questions

Can the Edge TPU perform accelerated ML training?

No, the first-generation Edge TPU is capable of accelerating ML inferencing only.

What machine learning frameworks does the Edge TPU support?

TensorFlow Lite only.

How do I create a TensorFlow Lite model for the Edge TPU?

You need to create a quantized TensorFlow Lite model and then compile the model for compatibility with the Edge TPU. We will provide a cloud-based compiler tool that accepts your .tflite file and returns a version that's compatible with the Edge TPU.

We will also provide several pre-compiled vision models that perform image classification and object detection.

What type of neural network does the Edge TPU support?

The first-generation Edge TPU is capable of executing deep feed-forward neural networks (DFF) such as convolutional neural networks (CNN), making it ideal for a variety of vision-based ML applications. The Edge TPU compiler will add support for various model architectures over time, as we verify compatibility and performance. In the first release, the Edge TPU compiler supports the following model architectures:

  • MobileNet V1/V2
    224x224 max input size; 1.0 max depth multiplier
  • MobileNet SSD V1/V2
    320x320 max input size; 1.0 max depth multiplier
  • Inception V1/V2
    224x224 fixed input size
  • Inception V3/V4
    299x299 fixed input size

How can I integrate the Edge TPU with my system?

The Edge TPU Dev Board is a single-board computer that includes an SOC and Edge TPU integrated on the SOM, so it's a complete system. You can also remove the SOM (or purchase it separately) and then integrate it with other hardware via three board-to-board connectors—even in this scenario, the SOM contains the complete system with SOC and Edge TPU, and all system interfaces (I2C, MIPI-CSI/DSI, SPI, etc.) are accessible via 300 pins on the board-to-board connectors so you can connect your hardware interfaces. Details will be provided in the datasheet.

With the Edge TPU Accelerator, you can simply connect to any Linux-based system with a USB cable (we recommend USB 3.0 for best performance).

How can I learn more?

Sign up here for updates.