Google Coral USB Accelerator

Product Information

The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port. Performs high-speed ML inferencing With that said, the table below compares the time spent to perform a single inference with several popular models on the Edge TPU. For the sake of comparison, all models running on both CPU and Edge TPU are the TensorFlow Lite versions.

Each Edge TPU coprocessor is capable of 4 billion arithmetic operations per second (4 TOPS) with 2-watt power consumption. For example, modern Mobile Vision models such as MobileNet v2 can run efficiently at close to 400 FPS. No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU. Tech specs The entry-level local AI project kits for voice and vision provide simple ways for designers to experiment with machine learning and enable developers to harness the power of AI and on-device inferencing to build intelligent solutions that can benefit a wide range of industries including the development of smart cities, manufacturing, automotive, healthcare and agriculture. Users can also easily bring high-speed ML inferencing to a range of existing systems using Coral’s USB accelerators. Note: These figures measure the time required to execute the model only. It does not include the time to process input data (such as down-scaling images to fit the input tensor), which can vary between systems and applications. These tests are also performed using C++ benchmark tests, whereas our public Python benchmark scripts may be slower due to overhead from Python. Model architectureThe Edge TPU runtime provides the core programming interface for the Edge TPU. You can install it on To run some other models, such as real-time object detection, pose estimation, keyphrase detection, The example above uses the PyCoral API, which calls into the TensorFlow Lite Python API, but you can Connects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10. Supports TensorFlow Lite Farnell Global trades as Farnell in Europe, Newark in North America, and element14 in Asia Pacific. It also sells direct to consumers through its CPC business in the UK.

An individual Edge TPU is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). How that translates to performance for your application depends on a variety of factors. Every neural network model has different demands, and if you're using the USB Accelerator device, total performance also varies based on the host CPU, USB speed, and other system resources. Connects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10. The Coral Edge TPU is a revolutionary product for machine learning applications. This enables embedded solutions that can, for example, recognize problems with workpieces, recognize traffic situations and much more. Resources The M.2 Accelerator with Dual Edge TPU is supported under Debian Linux based systems as well as under Windows 10.Simply connect via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10 and you’re good to go! It’s a versatile little gadget that can be integrated into various setups. You won’t need to build models from the ground up either. TensorFlow Lite models can be compiled to run seamlessly on the Edge TPU.