Neural-nets on a Movidius compute stick
Using a neural-net-in-a-dongle to recognise objects.

Why?

Because a Raspberry Pi isn't going to run a neural net all that quickly, and sometimes you have to throw computing power and ingenuity at a problem, like a Movidius Compute Stick.

Process

Yours truly bought a stick. It's not actually a 'Movidius', but a 'Neural Compute Stick II'. I guess they are trying to move away from the Movidius name or something.

Conclusion

Hmm .. bit soon for conclusions.

The future

More stuff.

Leave a comment

Something I'm doing wrong? Solved my problems? Got a better idea? Got a similar problem?
Think I might have solved your problem? Ninety-nine problems, but your robot ain't one? Say so ..