The TensorFlow.js Node.js environment supports using an installed build of Python/C TensorFlow as a back end, which may in turn use the machine’s available hardware acceleration, for example CUDA.

TensorFlow.js, as the JavaScript TensorFlow library is called, uses the WebGL API to accelerate computations by way of whatever GPUs are available in the system.

Explaining how to get up to speed with your TensorFlow Lite kit. Check out the 10 minute tutorial video below or jump over to the official Adafruit online resource centre for more details.