|
|
@@ -29,13 +29,13 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
|
|
|
## Main Results
|
|
|
COCO
|
|
|
|
|
|
-| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
|
|
+| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(G) |
|
|
|
| :----------------------------------------------------------------------------------- | :-------------------: | :-------------------:| :------------------------------:| :-----------------:| :---------------:|
|
|
|
-| [YOLO12n](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolo12n.pt) | 640 | xx.x | x.xx | 2.5 | 6.6 |
|
|
|
-| [YOLO12s](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolo12s.pt) | 640 | xx.x | x.xx | 8.9 | 22.0 |
|
|
|
-| [YOLO12m](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolo12m.pt) | 640 | xx.x | x.xx | 19.9 | 69.7 |
|
|
|
-| [YOLO12l](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolo12l.pt) | 640 | xx.x | x.xx | 28.3 | 97.2 |
|
|
|
-| [YOLO12x](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolo12x.pt) | 640 | xx.x | xx.x | 63.2 | 216.5 |
|
|
|
+| [YOLO12n](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolov12n.pt) | 640 | 40.6 | 1.64 | 2.6 | 6.5 |
|
|
|
+| [YOLO12s](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolov12s.pt) | 640 | 48.0 | 2.61 | 9.3 | 21.4 |
|
|
|
+| [YOLO12m](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolov12m.pt) | 640 | 52.5 | 4.86 | 20.2 | 67.5 |
|
|
|
+| [YOLO12l](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolov12l.pt) | 640 | 53.7 | 6.77 | 26.4 | 88.9 |
|
|
|
+| [YOLO12x](https://github.com/sunsmarterjie/assets/releases/download/v1.0/yolov12x.pt) | 640 | 55.2 | 11.79 | 59.1 | 199.0 |
|
|
|
|
|
|
## Installation
|
|
|
```
|
田运杰