36.9 C
Bucharest
Thursday, June 20, 2024

This Add-On Brings AI to Your Raspberry Pi: Here’s How It Works

Key Takeaways

  • The Raspberry Pi AI Kit enhances Raspberry Pi 5 with an entry-level 13 TOPS NPU for AI workloads.
  • The kit supports various tasks like object detection, image segmentation, and pose estimation with low latency for IoT applications.
  • Raspberry Pi AI Kit limitations include power draw and limited PCI Express lanes, yet it boosts AI tasks efficiency on the Raspberry Pi 5.


MUO VIDEO OF THE DAY

SCROLL TO CONTINUE WITH CONTENT

The Raspberry Pi 5 is a versatile single-board computer that balances price, performance, and power efficiency. However, it lacks one defining feature most modern computers are pushing toward: a neural processing unit, or NPU for short.

The Raspberry Pi Foundation feels your pain and as such, has launched the Raspberry Pi AI Kit.


What Is the Raspberry Pi AI Kit?

<div class="responsive-img image-expandable img-article-item" style="padding-bottom:66.666666666667%" data-img-url="https://static1.makeuseofimages.com/wordpress/wp-content/uploads/2024/06/raspberry_pi_ai_kit_dissassembled.jpg" data-modal-id="single-image-modal" data-modal-container-id="single-image-modal-container" data-img-caption=""Raspberry Pi””>

Raspberry Pi AI Kit Dissassembled
Raspberry Pi

The Raspberry Pi AI Kit is essentially Raspberry Pi’s new M.2 HAT+ board integrated with a Hailo-8L accelerator module.

The Hailo-8L module is an entry-level accelerator module capable of up to 13 tera-operations per second (TOPS) of real-time, low-latency inferencing performance (for context, Intel’s Meteor Lake laptop chips deliver about 10 TOPS, while its new Lunar Lake chips will deliver up to 40 TOPS). The M.2 HAT allows it to interface with the Raspberry Pi 5, enabling the computer to easily process AI workloads such as object detection, image segmentation, and pose estimation.


A major advantage of running AI workloads on the NPU is that it lowers power consumption and frees the main processor on the Raspberry Pi 5 for other computing tasks. The Raspberry Pi AI kit is compatible with first-party and third-party camera modules and simultaneously supports load sharing with multiple cameras.

The kit also includes a 16mm GPIO stacking header, a thermal pad between the HAT+ and the module, as well as spacers and screws for mounting the AI Kit on the Raspberry Pi 5. It is available on pre-order for $70 from CanaKit and other approved Raspberry Pi resellers.

What Can You Use The Raspberry Pi AI Kit For?

Apart from the Raspberry Pi 5, you will need certain hardware and software to use the AI Kit to its full potential. This includes an up-to-date installation of the 64-bit Bookworm operating system and a Raspberry Pi camera module.

A Raspberry Pi 5 device running an up-to-date 64-bit Bookworm image will detect the Hailo module automatically and directly support neural network processes to the NPU. This works via the built-in rpi-cam apps software library in the Raspberry Pi operating system.


So, what are the potential uses of the Raspberry Pi AI Kit? The kit is primarily targeted at computer vision projects, i.e., applications enabling a computer to understand and derive insights from still or moving images. The Raspberry Pi AI Kit can be used to accelerate tasks such as:

  • Object detection/recognition, which displays descriptive text and objects detected by the neural network
  • Image segmentation, which involves the neural network performing object detection and segmenting different objects using color masks
  • Pose estimation detects up to 17 key points relating to the position and orientation of each person and object in the image.


These capabilities can find applications in home automation, security, advanced vision-guided robotics, industrial process control, and even in building a 51 TOPS AI computer, as Jeff Geerling demonstrated in his video (as long as you can figure out the power issue!).

Hailo’s Raspberry Pi 5 examples repository hosts some handy demos. Also, Hailo’s model zoo contains many pre-trained neural networks, which can serve as a springboard for your embedded projects.

Be sure to refer to Raspberry Pi’s official documentation for the AI Kit, which includes an installation guide, a getting started guide, and other resources.

The Raspberry Pi AI Kit Has Some Limitations

The Raspberry Pi company has partnered with AI startup Hailo to create a kit that expands the potential of the Raspberry Pi 5. However, it has limitations.


For example, the Raspberry Pi 5 is a low-cost single-board computer that draws a small amount of power and has only one PCI Express lane to interface with the AI Kit. Therefore, the AI Kit is not going to replace ChatGPT or DALL-E, but it will allow certain AI-computing tasks to run speedily and efficiently on the Raspberry Pi 5.

Still, it’s a nifty little upgrade for the Raspberry Pi, and having on-device AI processing will open even more doors for how the Raspberry Pi 5 can be used.

Link

- Advertisement -
Latest
- Advertisement -spot_img

More Articles

- Advertisement -spot_img