— Benchmarks for running AI in microcontrollers
https://qengineering.eu/deep-learning-with-raspberry-pi-and-alternatives.html
| Model | Framework | Raspberry Pi (TF-Lite) | Raspberry Pi (ncnn) | Raspberry PiIntel Neural Stick 2 | Raspberry PiGoogle Coral USB | JeVois | Jetson Nano | Google Coral |
|---|---|---|---|---|---|---|---|---|
| EfficientNet-B0(224x224) | TF | 14.6 FPS (Pi 3) 25.8 FPS (Pi 4) | - | 95 FPS (Pi 3) 180 FPS (Pi 4) | 105 FPS (Pi 3) 200 FPS (Pi 4) | - | 216 FPS | 200 FPS |
| ResNet-50(244x244) | TF | 2.4 FPS (Pi 3) 4.3 FPS (Pi 4) | 1.7 FPS (Pi 3) 3 FPS (Pi 4) | 16 FPS (Pi 3) 60 FPS (Pi 4) | 10 FPS (Pi 3) 18.8 FPS (Pi 4) | - | 36 FPS | 18.8 FPS |
| MobileNet-v2(300x300) | TF | 8.5 FPS (Pi 3) 15.3 FPS (Pi 4) | 8 FPS (Pi 3) 8.9 FPS (Pi 4) | 30 FPS (Pi 3) | 46 FPS (Pi 3) | 30 FPS | 64 FPS | 130 FPS |
| SSD Mobilenet-V2(300-300) | TF | 7.3 FPS (Pi 3) 13 FPS (Pi 4) | 3.7 FPS (Pi 3) 5.8 FPS (Pi 4) | 11 FPS (Pi 3) 41 FPS (Pi 4) | 17 FPS (Pi 3) 55 FPS (Pi 4) | - | 39 FPS | 48 FPS |
| Inception V4(299x299) | PyTorch | - | - | - | 3 FPS (Pi 3) | - | 11 FPS | 9 FPS |
| Tiny YOLO V3(416x416) | Darknet | 0.5 FPS (Pi 3) 1 FPS (Pi 4) | 1.1 FPS (Pi 3) 1.9 FPS (Pi 4) | - | - | 2.2 FPS | 25 FPS | - |
| OpenPose(256x256) | Caffe | 4.3 FPS (Pi 3) 10.3 FPS (Pi 4) | - | 5 FPS (Pi 3) | - | - | 14 FPS | - |
| Super Resolution(481x321) | PyTorch | - | - | 0.6 FPS (Pi 3) | - | - | 15 FPS | - |
| VGG-19(224x224) | MXNet | 0.5 FPS (Pi 3) 1 FPS (Pi 4) | - | 5 FPS | - | - | 10 FPS | - |
| Unet(1x512x512) | Caffe | - | - | 5 FPS | - | - | 18 FPS | - |
| Unet(3x257x257) | TF | 2.0 FPS (Pi 3) 3.6 FPS (Pi 4) |