Google has released its edge AI devices notably the Coral Dev Board and the USB Accelerator recently and I managed to buy the USB accelerator from Seeed Studio before it was sold out. I find that there is a bit of irony that China is listed as one of the countries that have restricted export but my Accelerator was shipped out of Shenzhen and luckily I do not stay in one of the countries listed that has export restrictions.
This is really a tiny piece of device. It is has a silver heat sink wrapped with rubbery plastic and comes with a USB 3.0 USB-C interface. I cannot imagine that this edge TPU only consumed about 2.5W but packed enough computation power to perform object detection and image classification in real-time. I decided to do my initial test on a Linux desktop that has USB 3 supports instead of Raspberry Pi in order to make sure that the USB port is not the bottleneck.
Installation was brisk, I have followed the Get Started Guide and I managed to get the demo app up and running within 20 mins. Google has provided a few pre-built models which can be directly used with the USB accelerator.
8 July Update: This blog post shows how to do transfer learning using Colab and later convert the model to be used in Edge TPU.
22 July Update: Another blog post on Transfer Learning and post-training quantization.
This is really a tiny piece of device. It is has a silver heat sink wrapped with rubbery plastic and comes with a USB 3.0 USB-C interface. I cannot imagine that this edge TPU only consumed about 2.5W but packed enough computation power to perform object detection and image classification in real-time. I decided to do my initial test on a Linux desktop that has USB 3 supports instead of Raspberry Pi in order to make sure that the USB port is not the bottleneck.
Installation was brisk, I have followed the Get Started Guide and I managed to get the demo app up and running within 20 mins. Google has provided a few pre-built models which can be directly used with the USB accelerator.
Conclusion
I am generally very happy with the USB Accelerator. It is going to be an exciting time. Next, I will try out real-time image classification and object detection.8 July Update: This blog post shows how to do transfer learning using Colab and later convert the model to be used in Edge TPU.
22 July Update: Another blog post on Transfer Learning and post-training quantization.
Thanks for sharing this Content Please checkout this What are the best digital marketing services in Lahore?
ReplyDeleteJust tried out the Coral USB Accelerator for the first time—really impressed with how much it speeds up TensorFlow Lite models. I tested it on a Raspberry Pi and saw a big boost in object detection performance. Super small device, easy setup, and runs models locally without needing cloud processing. Great little tool for edge AI projects!
ReplyDeleteBy the way, if you're into writing about tech or AI hardware, I recently found this great platform that accepts guest posts: Write for us Technology. Worth checking out if you want to share your insights!