Benchmarks
The Hailo-8™ AI Processor brings industry-leading neural processing throughput and power efficiency to support a wide range of AI applications.
The table below demonstrates some of Hailo-8’s best-in-class capabilities in the foundational neural tasks of object detection and classification. It achieves very high FPS and power efficiency (FPS/W) across a number of industry-standard neural network models, while also offloading postprocessing from the host processor its working with.
Benchmarks
NN Model | Type | Input Resolution | FPS | Power [W] | FPS/ W |
---|---|---|---|---|---|
ResNet_v1_50 | Classification | 224×224 | 1,328 | 3.1 | 428 |
MobileNet_v2_1.0 | Classification | 224×224 | 2,613 | 2.1 | 1267 |
MobileNet_v3 * | Classification | 224×224 | 3,468 | 1.8 | 1878 |
Regnetx-800MF | Classification | 224×224 | 2,447 | 2.0 | 1232 |
EfficientNet_M | Classification | 240×240 | 889 | 3.2 | 278 |
SSD_MobileNet_v1 | Object Detection | 300×300 | 1,038 | 2.3 | 452 |
Tiny_YOLOv3 | Object Detection | 416×416 | 1,010 | 3.2 | 315 |
YOLOv3 ** | Object Detection | 608×608 | 60 | 4.2 | 14 |
YOLOv4 ** | Object Detection | 512×512 | 72 | 3.1 | 23 |
YOLOv5m | Object Detection | 640×640 | 218 | 4.3 | 50 |
* MobileNet_v3 – the benchmarked model flavor is MobileNet_v3 Large Minimalistic
** Figure for processing 8 simultaneous video streams
Notes:
– Based on SDK version 3.14.0 (Q1 2022)
– Measurements are done at room temperature on a single Hailo-8 device through PCIe interface on a Hailo evaluation board
– System host: Intel® Core™ i5-9400 CPU @ 2.90GHz
Hailo-8 outperforms other edge AI processors on the market on common benchmarks.
Click here and here to see how it compares.