Implementing a pretrained CIFAR-10 network

First, if you were just running the hello_world.py script, go ahead and stop the script from executing by pressing the stop button in the lower left-hand corner of the OpenMV IDE. This will get you back to square one and ensure that nothing interferes with our ability to load the CIFAR-10 example.

Next, before we can execute the example code, we need to save the CIFAR-10 trained network interface on the OpenMV camera. This will provide the camera with the trained network and we will need to reference it in our application script. Perform the following steps to load and save the CIFAR-10 network file:

  1. From the top menu, click Tools | Machine Learning | CNN Network Library.
  2. In the pop-up window, navigate ...

Get MicroPython Projects now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.