|
|
@@ -56,7 +56,7 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
|
|
|
## Main Results
|
|
|
|
|
|
**Turbo (default version)**:
|
|
|
-| 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) |
|
|
|
+| Model (det) | 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/yolov12/releases/download/turbo/yolov12n.pt) | 640 | 40.4 | 1.60 | 2.5 | 6.0 |
|
|
|
| [YOLO12s](https://github.com/sunsmarterjie/yolov12/releases/download/turbo/yolov12s.pt) | 640 | 47.6 | 2.42 | 9.1 | 19.4 |
|
|
|
@@ -65,7 +65,7 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
|
|
|
| [YOLO12x](https://github.com/sunsmarterjie/yolov12/releases/download/turbo/yolov12x.pt) | 640 | 55.4 | 10.38 | 59.3 | 184.6 |
|
|
|
|
|
|
[**v1.0**](https://github.com/sunsmarterjie/yolov12/tree/V1.0):
|
|
|
-| 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) |
|
|
|
+| Model (det) | 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/yolov12/releases/download/v1.0/yolov12n.pt) | 640 | 40.6 | 1.64 | 2.6 | 6.5 |
|
|
|
| [YOLO12s](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12s.pt) | 640 | 48.0 | 2.61 | 9.3 | 21.4 |
|
|
|
@@ -74,7 +74,7 @@ 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 | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<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<br><sup>T4 TensorRT10<br> | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
|
|
| :------------------------------------------------------------------------------------| :--------------------: | :-------------------: | :---------------------: | :--------------------------------:| :------------------: | :-----------------: |
|
|
|
| [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 |
|
田运杰