Demos and Benchmarks
See the Ergo AI processors in action
Presented by Perceive CEO Steve Teig at CES 2023, this video showcases the exceptional performance and power-efficiency of the Ergo chips in two demos: Ergo running ResNet-50 at 30 fps to do image classification and Ergo 2 running 17-key-point body pose estimation at 30 fps.
Powerful, power-efficient performance for edge AI
Perceive Ergo® AI processors enable product developers to leverage large neural networks capable of delivering advanced features, while operating within tight power constraints. The following table provides some performance and power-efficiency benchmarks, based on our own testing with several well-known neural networks.
| Ergo | Ergo 2 | |||||||
|---|---|---|---|---|---|---|---|---|
| Max App IPS* | Compute Power @ 30 fps (mW) | Power Efficiency (IPS/W) | Max App IPS | Compute Power @ 30 fps (mW) | Power Efficiency (IPS/W) | |||
| Image Classification | ||||||||
| MobileNet-v2 | 280 | 9 | 3284 | 1286 | 17 | 3854 | ||
| ResNet-50 | 262 | 11 | 2727 | 1024 | 17 | 3434 | ||
| Object Detection | ||||||||
| YOLO-v5-S | 44 | 50 | 600 | 122 | 79 | 436 | ||
* Inferences per second
Don't see your network here?
This is not an exhaustive list of the neural networks supported by the Ergo product line – please get in touch with us to discuss your specific needs.