Update README.md

README.md

@@ -77,7 +77,7 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
 | [YOLO12x](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12x.pt) | 640                   | 55.2                 | 11.79                           | 59.1               | 199.0             |
 
 [**Instance segmentation**](https://github.com/sunsmarterjie/yolov12/tree/Seg):
-| Model (seg)                                                                              | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed  (ms) <br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(B) |
+| Model (seg)                                                                              | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed  (ms) <br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(G) |
 | :------------------------------------------------------------------------------------| :--------------------: | :-------------------: | :---------------------: | :--------------------------------:| :------------------: | :-----------------: |
 | [YOLOv12n-seg](https://github.com/sunsmarterjie/yolov12/releases/download/seg/yolov12n-seg.pt) | 640                   | 39.9                 | 32.8                  | 1.84                           | 2.8                | 9.9              |
 | [YOLOv12s-seg](https://github.com/sunsmarterjie/yolov12/releases/download/seg/yolov12s-seg.pt) | 640                   | 47.5                 | 38.6                  | 2.84                           | 9.8                | 33.4              |
@@ -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><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) |
+| 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>(G) |
 | :----------------------------------------------------------------------------------------| :-------------------: | :------------: | :------------: | :-------------------------------------:| :----------------: | :---------------: |
 | [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               |