|
|
@@ -87,7 +87,7 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
|
|
|
|
|
|
|
|
|
[**Classification**](https://github.com/sunsmarterjie/yolov12/tree/Cls):
|
|
|
-| Model (cls) | size<br><sup>(pixels) | Acc.<br>top-1<br> | Acc.<br>top-5<br> | Speed (ms) <br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
|
|
+| Model (cls) | size<br><sup>(pixels) | Acc.<br><sup>top-1<br> | Acc.<br><sup>top-5<br> | Speed (ms) <br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
|
|
| :----------------------------------------------------------------------------------------| :-------------------: | :------------: | :------------: | :-------------------------------------:| :----------------: | :---------------: |
|
|
|
| [YOLOv12n-cls](https://github.com/sunsmarterjie/yolov12/releases/download/cls/yolov12n-cls.pt) | 224 | 71.7 | 90.5 | 1.27 | 2.9 | 0.5 |
|
|
|
| [YOLOv12s-cls](https://github.com/sunsmarterjie/yolov12/releases/download/cls/yolov12s-cls.pt) | 224 | 76.4 | 93.3 | 1.52 | 7.2 | 1.5 |
|
田运杰