- Object Detection
Quick Search supports to train a model based on open sources and NPNets will be available with Advanced Search.
YOLOv5 and YOLOv5-NPNets
| Dataset | Model | mAP(0.5) (%) | mAP(0.5:0.95) (%) | GFLOPs | Parameters (M) | Model Size (MB) |
|---|---|---|---|---|---|---|
| PASCAL VOC | YOLOv5n | 72.2 | 44 | 4.3 | 1.79 | 3.62 |
| PASCAL VOC | YOLOv5n-NPNet | 73.4 | 46.3 | 3.5 | 1.18 | 2.49 |
| PASCAL VOC | YOLOv5s | 77.9 | 52.2 | 16 | 7.07 | 13.7 |
| PASCAL VOC | YOLOv5s-NPNet | 80.2 | 56 | 12.8 | 4.61 | 9.05 |
| PASCAL VOC | YOLOv5m | 82.1 | 59.3 | 48.3 | 20.95 | 40.2 |
| PASCAL VOC | YOLOv5m-NPNet | 83.4 | 60.6 | 37 | 12.26 | 23.7 |
| PASCAL VOC | YOLOv5l | 82.9 | 61 | 108.3 | 46.24 | 88.6 |
| PASCAL VOC | YOLOv5l-NPNet | 85.1 | 63.8 | 81 | 25.19 | 48.5 |
Updated about 2 months ago