Blogs

improved inference speed on rpi3 using Intel's NCS1

Posted by andre van calster on October 13, 2019 at 4:52am

By using Intels OpenVINO and neural computing stick (NCS1) the inference speed of my neural network is increased from 5 frames per second (fps) to 20 using a RPI3. This enabled a far better obstacle avoidance performance of my drone. More info at https://github.com/avncalst/drone_cnn.

cnn, openvino, quadcopter

E-mail me when people leave their comments –

You need to be a member of diydrones to add comments!

Join diydrones

Comments

andre van calster October 23, 2019 at 9:03am

A faster inference is achieved using Intel's NCS2
andre van calster October 15, 2019 at 9:24am

Thx Rana. There is a short wiki (on my git page, tab wiki) describing my project. I included a link to this wiki in the README.md file.
Rana October 15, 2019 at 6:31am

Great efforts n great results indeed ! There is no wiki on the git page which you should do asap, it should include wiring diagram, BOM and more which you think, is required for anyone interested to test it.
andre van calster October 14, 2019 at 1:16am

thx
Andreas Gazis October 13, 2019 at 11:52pm

Very nice, I love watching your videos.

This reply was deleted.

#xg { position:relative;top:120px; } #xn_bar { top:120px; }

Hello, you need to enable JavaScript to use diydrones.

Please check your browser settings or contact your system administrator.