When using the Raspberry Pi for deep learning we have two major pitfalls working against us:
Restricted memory (only 1GB on the Raspberry Pi 3).
Limited processor speed.
This makes it near impossible to use larger, deeper neural networks.
Instead, we need to use more computationally efficient networks with a smaller memory/processing footprint such as MobileNet and SqueezeNet. These networks are more appropriate for the Raspberry Pi; however, you need to set your expectations accordingly — you should not expect blazing fast speed.
Each Friday is PiDay here at Adafruit! Be sure to check out our posts, tutorials and new Raspberry Pi related products. Adafruit has the largest and best selection of Raspberry Pi accessories and all the code & tutorials to get you up and running in no time!