Skip to content

Coral Edge TPU on a Raspberry Pi with Ultralytics YOLO11 🚀

Raspberry Pi single board computer with USB Edge TPU accelerator

What is a Coral Edge TPU?

The Coral Edge TPU is a compact device that adds an Edge TPU coprocessor to your system. It enables low-power, high-performance ML inference for TensorFlow Lite models. Read more at the Coral Edge TPU home page.



Watch: How to Run Inference on Raspberry Pi using Google Coral Edge TPU

Boost Raspberry Pi Model Performance with Coral Edge TPU

Many people want to run their models on an embedded or mobile device such as a Raspberry Pi, since they are very power efficient and can be used in many different applications. However, the inference performance on these devices is usually poor even when using formats like ONNX or OpenVINO. The Coral Edge TPU is a great solution to this problem, since it can be used with a Raspberry Pi and accelerate inference performance greatly.

Edge TPU on Raspberry Pi with TensorFlow Lite (New)⭐

The existing guide by Coral on how to use the Edge TPU with a Raspberry Pi is outdated, and the current Coral Edge TPU runtime builds do not work with the current TensorFlow Lite runtime versions anymore. In addition to that, Google seems to have completely abandoned the Coral project, and there have not been any updates between 2021 and 2024. This guide will show you how to get the Edge TPU working with the latest versions of the TensorFlow Lite runtime and an updated Coral Edge TPU runtime on a Raspberry Pi single board computer (SBC).

Prerequisites

Installation Walkthrough

This guide assumes that you already have a working Raspberry Pi OS install and have installed ultralytics and all dependencies. To get ultralytics installed, visit the quickstart guide to get setup before continuing here.

Installing the Edge TPU runtime

First, we need to install the Edge TPU runtime. There are many different versions available, so you need to choose the right version for your operating system.

Raspberry Pi OS High frequency mode Version to download
Bullseye 32bit No libedgetpu1-std_ ... .bullseye_armhf.deb
Bullseye 64bit No libedgetpu1-std_ ... .bullseye_arm64.deb
Bullseye 32bit Yes libedgetpu1-max_ ... .bullseye_armhf.deb
Bullseye 64bit Yes libedgetpu1-max_ ... .bullseye_arm64.deb
Bookworm 32bit No libedgetpu1-std_ ... .bookworm_armhf.deb
Bookworm 64bit No libedgetpu1-std_ ... .bookworm_arm64.deb
Bookworm 32bit Yes libedgetpu1-max_ ... .bookworm_armhf.deb
Bookworm 64bit Yes libedgetpu1-max_ ... .bookworm_arm64.deb

Download the latest version from here.

After downloading the file, you can install it with the following command:

sudo dpkg -i path/to/package.deb

After installing the runtime, you need to plug in your Coral Edge TPU into a USB 3.0 port on your Raspberry Pi. This is because, according to the official guide, a new udev rule needs to take effect after installation.

Important

If you already have the Coral Edge TPU runtime installed, uninstall it using the following command.

# If you installed the standard version
sudo apt remove libedgetpu1-std

# If you installed the high frequency version
sudo apt remove libedgetpu1-max

Export your model to a Edge TPU compatible model

To use the Edge TPU, you need to convert your model into a compatible format. It is recommended that you run export on Google Colab, x86_64 Linux machine, using the official Ultralytics Docker container, or using Ultralytics HUB, since the Edge TPU compiler is not available on ARM. See the Export Mode for the available arguments.

Exporting the model

from ultralytics import YOLO

# Load a model
model = YOLO("path/to/model.pt")  # Load an official model or custom model

# Export the model
model.export(format="edgetpu")
yolo export model=path/to/model.pt format=edgetpu  # Export an official model or custom model

The exported model will be saved in the <model_name>_saved_model/ folder with the name <model_name>_full_integer_quant_edgetpu.tflite. It is important that your model ends with the suffix _edgetpu.tflite, otherwise ultralytics doesn't know that you're using a Edge TPU model.

Running the model

Before you can actually run the model, you will need to install the correct libraries.

If tensorflow is installed, uninstall tensorflow with the following command:

pip uninstall tensorflow tensorflow-aarch64

Then install/update tflite-runtime:

pip install -U tflite-runtime

Now you can run inference using the following code:

Running the model

from ultralytics import YOLO

# Load a model
model = YOLO("path/to/<model_name>_full_integer_quant_edgetpu.tflite")  # Load an official model or custom model

# Run Prediction
model.predict("path/to/source.png")
yolo predict model=path/to/<model_name>_full_integer_quant_edgetpu.tflite source=path/to/source.png  # Load an official model or custom model

Find comprehensive information on the Predict page for full prediction mode details.

Inference with multiple Edge TPUs

If you have multiple Edge TPUs you can use the following code to select a specific TPU.

from ultralytics import YOLO

# Load a model
model = YOLO("path/to/<model_name>_full_integer_quant_edgetpu.tflite")  # Load an official model or custom model

# Run Prediction
model.predict("path/to/source.png")  # Inference defaults to the first TPU

model.predict("path/to/source.png", device="tpu:0")  # Select the first TPU

model.predict("path/to/source.png", device="tpu:1")  # Select the second TPU

FAQ

What is a Coral Edge TPU and how does it enhance Raspberry Pi's performance with Ultralytics YOLO11?

The Coral Edge TPU is a compact device designed to add an Edge TPU coprocessor to your system. This coprocessor enables low-power, high-performance machine learning inference, particularly optimized for TensorFlow Lite models. When using a Raspberry Pi, the Edge TPU accelerates ML model inference, significantly boosting performance, especially for Ultralytics YOLO11 models. You can read more about the Coral Edge TPU on their home page.

How do I install the Coral Edge TPU runtime on a Raspberry Pi?

To install the Coral Edge TPU runtime on your Raspberry Pi, download the appropriate .deb package for your Raspberry Pi OS version from this link. Once downloaded, use the following command to install it:

sudo dpkg -i path/to/package.deb

Make sure to uninstall any previous Coral Edge TPU runtime versions by following the steps outlined in the Installation Walkthrough section.

Can I export my Ultralytics YOLO11 model to be compatible with Coral Edge TPU?

Yes, you can export your Ultralytics YOLO11 model to be compatible with the Coral Edge TPU. It is recommended to perform the export on Google Colab, an x86_64 Linux machine, or using the Ultralytics Docker container. You can also use Ultralytics HUB for exporting. Here is how you can export your model using Python and CLI:

Exporting the model

from ultralytics import YOLO

# Load a model
model = YOLO("path/to/model.pt")  # Load an official model or custom model

# Export the model
model.export(format="edgetpu")
yolo export model=path/to/model.pt format=edgetpu  # Export an official model or custom model

For more information, refer to the Export Mode documentation.

What should I do if TensorFlow is already installed on my Raspberry Pi but I want to use tflite-runtime instead?

If you have TensorFlow installed on your Raspberry Pi and need to switch to tflite-runtime, you'll need to uninstall TensorFlow first using:

pip uninstall tensorflow tensorflow-aarch64

Then, install or update tflite-runtime with the following command:

pip install -U tflite-runtime

For a specific wheel, such as TensorFlow 2.15.0 tflite-runtime, you can download it from this link and install it using pip. Detailed instructions are available in the section on running the model Running the Model.

How do I run inference with an exported YOLO11 model on a Raspberry Pi using the Coral Edge TPU?

After exporting your YOLO11 model to an Edge TPU-compatible format, you can run inference using the following code snippets:

Running the model

from ultralytics import YOLO

# Load a model
model = YOLO("path/to/edgetpu_model.tflite")  # Load an official model or custom model

# Run Prediction
model.predict("path/to/source.png")
yolo predict model=path/to/edgetpu_model.tflite source=path/to/source.png  # Load an official model or custom model

Comprehensive details on full prediction mode features can be found on the Predict Page.

📅 Created 9 months ago ✏️ Updated 1 month ago

Comments