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.
Comments
Post a Comment