Seeed and Coral are glad to partner together to bring this global education program to help educators and students across the globe transform on-device AI application ideas from prototype to production. If you are a student or an educator looking for embedded AI solutions or want hands-on AI learning, don’t hesitate to join Coral Global Education program to receive an exclusive discount for students and educators. Register your interest here: https://forms.gle/3U7YWRbMkXX7jgBm9. Please fill out the questionnaire to be considered for this program. We will offer a 35% discount off of the Coral Dev Board 1GB list price of $129.99 to qualified applicants. The discount is only available to current and newly accepted educational organization students, as well as, faculty, staff, and teachers of all grade levels.
About Coral Dev Board
Google Coral Dev Board is a single-board computer that contains an Edge TPU coprocessor, composed of the Edge TPU Module (SOM) and a development baseboard. The SOM is based on NXP’s iMX8M system-on-chip (SOC), but its unique power comes from the Edge TPU coprocessor. Google TPU Coral Dev Board works with the best of Google’s ML tools, including TensorFlow and Cloud. Seeed also updated Grove.py Python Library for Grove modules support Coral Dev Board now, which means you can use Grove modules by plug-and-play for quick prototypes.
Edge TPU key benefits
- High-speed TensorFlow Lite inferencing
- Low Power
- Small footprint
The dev board includes all the peripheral connections you need to prototype a project, including USB 2.0/3.0 ports, DSI display interface, CSI2 camera interface, Ethernet port, speaker terminals, and a 40-pin GPIO header.
It’s ideal for prototyping new projects that demand fast on-device inferencing for machine learning models.
How to get the discount？
- Please fill out the questionnaire at this form: https://forms.gle/ZjG3MgjeH8ndaLmt5 to be considered for this program. We will offer 35% discount off for the Coral Dev Board 1GB list price of $129.99 to qualified applicants.
- Please use the email provided by your educational institution.
- The discount is only available to current and newly accepted educational organization students, as well as, faculty, staff, and teachers of all grade levels.
- Once your application approved, we will send a unique coupon code to the email account you registered on our Seeed Studio online store. Please make sure you register with the email address provided by your educational organization.
- Feel free to email [email protected] to find out more about the education pricing program.
Start the Edge AI hands-on Coral Dev Board
Google has been working on a flexible development system for a couple of years, bringing Coral product line including Google Coral Edge TPU Dev. Board, USB Accelerator and camera that makes it easy for all AI developers and enthusiasts to grow embedded AI products into reality. Coral works with the best of Google’s ML tools, TensorFlow Lite. Supported OS: Debian Linux. Coral edge AI solution is:
- Private: Keep user data local and under your control
- Fast: Accelerate AI locally, inference times down to 2 ms
- Efficient: Low power demand to allow embedded applications
- Offline: Deploy in the field where connectivity is limited
Access to Edge AI in a cost-effective, locally but powerful way
Deep Learning and Machine learning are used to associate with big computers with fast CPUs and GPUs, big RAM size, or running algorithms on the cloud. With embedded AI, computing has been much more achievable and accessible. We have introduced Edge Computing is a distributed computing paradigm that brings computation and data storage closer to the devices where it’s being gathered. Edge Computing can process locally like a computer, IoT device, or Edge Server. By bringing computation to a network edge, long-distance communication between a client and server is now being reduced.
The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power-efficient manner. See more performance benchmarks.
AI at the Edge
With devices like Coral Dev Board, data can be curated before sending it off to a remote location for further analysis. Together with the availability of various field sensor data, intelligent IoT management is now possible with AI at the edge. Inference can now happen at the edge and decreases the amount of network traffic flowing back to the cloud with the response time for IoT devices being cut to a minimum as well as management decisions will be available on-premise which is close to the devices which can bring many advantages.
As you can see above, IoT configurations used to be like this where sensors or devices are connected directly to the internet providing raw data to a backend server where machine learning algorithms are run. What about now?
As u can see above, what you are seeing now is Edge AI where machine learning algorithms are being run locally on a hardware device or embedded systems as compared to on servers.
The Coral and Seeed teams are looking forward to meeting you in this AI and ML journey together 🙂