|
|
@@ -21,7 +21,8 @@
|
|
|
## Updates
|
|
|
|
|
|
- 2025/06/17: **Use this repo for YOLOv12 instead of [ultralytics](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/12). Their implementation is inefficient, requires more memory, and has unstable training, which are fixed here!**
|
|
|
-
|
|
|
+
|
|
|
+- 2025/07/01: YOLOv12's **classification** models are released, see [code](https://github.com/sunsmarterjie/yolov12/tree/Cls).
|
|
|
- 2025/06/04: YOLOv12's **instance segmentation** models are released, see [code](https://github.com/sunsmarterjie/yolov12/tree/Seg).
|
|
|
|
|
|
- 2025/04/15: Pretrain a YOLOv12 model with [LightlyTrain](https://docs.lightly.ai/train/stable/index.html), a novel framework that lets you pretrain any computer vision model on your unlabeled data, with [YOLOv12 support](https://docs.lightly.ai/train/stable/models/yolov12.html). Here is also a [Colab tutorial](https://colab.research.google.com/github/lightly-ai/lightly-train/blob/main/examples/notebooks/yolov12.ipynb)!
|
|
|
@@ -84,6 +85,16 @@ YOLOv12 surpasses all popular real-time object detectors in accuracy with compet
|
|
|
| [YOLOv12l-seg](https://github.com/sunsmarterjie/yolov12/releases/download/seg/yolov12l-seg.pt) | 640 | 54.0 | 43.2 | 7.61 | 28.8 | 137.7 |
|
|
|
| [YOLOv12x-seg](https://github.com/sunsmarterjie/yolov12/releases/download/seg/yolov12x-seg.pt) | 640 | 55.2 | 44.2 | 15.43 | 64.5 | 308.7 |
|
|
|
|
|
|
+
|
|
|
+[**Classification**](https://github.com/sunsmarterjie/yolov12/tree/Cls):
|
|
|
+| Model (cls) | size<br><sup>(pixels) | Acc.<sup>top-1 | Acc.<sup>top-5 | 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 |
|
|
|
+| [YOLOv12m-cls](https://github.com/sunsmarterjie/yolov12/releases/download/cls/yolov12m-cls.pt) | 224 | 78.8 | 94.4 | 2.03 | 12.7 | 4.5 |
|
|
|
+| [YOLOv12l-cls](https://github.com/sunsmarterjie/yolov12/releases/download/cls/yolov12l-cls.pt) | 224 | 79.5 | 94.5 | 2.73 | 16.8 | 6.2 |
|
|
|
+| [YOLOv12x-cls](https://github.com/sunsmarterjie/yolov12/releases/download/cls/yolov12x-cls.pt) | 224 | 80.1 | 95.3 | 3.64 | 35.5 | 13.7 |
|
|
|
+
|
|
|
</details>
|
|
|
|
|
|
|
田运杰