Edge TPU FAQ

If this page does not answer your question, please refer to our support channels.

What is the Edge TPU?

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.

We offer multiple products that include the Edge TPU built-in.

Two Edge TPU chips on the head of a US penny

What machine learning frameworks does the Edge TPU support?

TensorFlow Lite only.

What type of neural networks 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.

For details on supported model architectures, see the model requirements.

What kind of performance does it actually provide?

Naturally, benchmark numbers can't tell you everything. Every neural network model has different demands, and if you're using the USB or PCI-E Accelerator device, total performance will also vary based on the host CPU and other system resources.

With that said, this table compares the time spent to perform an inference with specific models.

Model architectureDesktop CPU*Desktop CPU *
+ USB Accelerator (USB 3.0)

with Edge TPU
Embedded CPU **Dev Board †
with Edge TPU
MobileNet v147 ms2.2 ms179 ms2.2 ms
MobileNet v245 ms2.3 ms150 ms2.5 ms
Inception v192 ms3.6 ms406 ms3.9 ms
Inception v4792 ms100 ms3,463 ms100 ms

* Desktop CPU: 64-bit Intel(R) Xeon(R) E5-1650 v4 @ 3.60GHz
** Embedded CPU: Quad-core Cortex-A53 @ 1.5GHz
Dev Board: Quad-core Cortex-A53 @ 1.5GHz + Edge TPU

All tested models were trained using the ImageNet dataset with 1,000 classes and an input size of 224x224, except for Inception v4 which has an input size of 299x299.

Can the Edge TPU perform accelerated ML training?

Sort of. The Edge TPU is not capable of backward propagation, which is required to perform traditional training on a model. However, using a technique described in Low-Shot Learning with Imprinted Weights, you can perform accelerated transfer-learning on the Edge TPU by embedding new vectors into the weights of the last fully-connected layer on a specially-built and pre-trained convolutional neural network (CNN).

For more information, read how to retrain an image classification model on-device.

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

You need to convert your model to TensorFlow Lite and it must be quantized. Then you need to compile the model for compatibility with the Edge TPU.

For more information, read TensorFlow models on the Edge TPU.

What's the difference between the Dev Board and the USB Accelerator?

The Coral 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.

Whereas, the Coral USB Accelerator is an accessory device that that adds the Edge TPU as a coprocessor to your existing system—you can simply connect it to any Linux-based system with a USB cable (we recommend USB 3.0 for best performance).

Can I buy just the Edge TPU chip?

No, we currently do not offer the standalone Edge TPU ASIC, but we do provide two products that make it easy to integrate the Edge TPU as a coprocessor for existing hardware systems using either USB 3.0 or a PCI-E interface. For details, see our products list.

If you have other specific requirements, please contact our sales team and we will be happy to discuss possible solutions.