English | 简体中文
Implementation of YOLOv6 paper:
- YOLOv6 v3.0: A Full-Scale Reloading 🔥
- YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
- [2024.02.12] Replace BACKBONE to lightweight models: ShuffleNetv2, GHostNet, MobileNetv3
- [2024.03.11] Update NECK to GolD-Neck
- [2024.04.09] Improved RepVGGBlock, get ACBlock
[3×3][1×3][3×1][1×1] - [2024.04.11] Improved Structure, get RepC2f
- [2024.04.15] Update RepOptimizer to adapt to ACBlock
| Model | Size | mAPval 0.5:0.95 |
SpeedT4 trt fp16 b1 (fps) |
SpeedT4 trt fp16 b32 (fps) |
Params (M) |
FLOPs (G) |
|---|---|---|---|---|---|---|
| YOLOv6-N | 640 | 37.5 | 779 | 1187 | 4.7 | 11.4 |
| YOLOv6-S | 640 | 45.0 | 339 | 484 | 18.5 | 45.3 |
| YOLOv6-M | 640 | 50.0 | 175 | 226 | 34.9 | 85.8 |
| YOLOv6-L | 640 | 52.8 | 98 | 116 | 59.6 | 150.7 |
| YOLOv6-N6 | 1280 | 44.9 | 228 | 281 | 10.4 | 49.8 |
| YOLOv6-S6 | 1280 | 50.3 | 98 | 108 | 41.4 | 198.0 |
| YOLOv6-M6 | 1280 | 55.2 | 47 | 55 | 79.6 | 379.5 |
| YOLOv6-L6 | 1280 | 57.2 | 26 | 29 | 140.4 | 673.4 |