Last spring I benchmarked machine learning inference on the MaaXBoard against similar single board computers. I looked at speed and power consumption while running inference using the object detection models MobileNet SSD V1 and V2.

Recently, I benchmarked the slightly faster MaaXBoard Mini against the same boards. Here are the results in graphs.

 

Results for speed:

Results for Power Consumption:

 

Results for Price:

Thanks for reading! I hope to benchmark more of Avnet's boards this year, so stay tuned. Finally, If you'd like to duplicate my results, all of the instructions are available in my projects on Hackster: