Add YOLOv12 model

jamjamjon · Feb 20, 2025 · fcc3ba9 · fcc3ba9
1 parent 018b884
commit fcc3ba9
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -34,7 +34,7 @@
 
 **usls** is a Rust library integrated with  **ONNXRuntime**, offering a suite of advanced models for **Computer Vision** and **Vision-Language** tasks, including:
 
-- **YOLO Models**: [YOLOv5](https://github.com/ultralytics/yolov5), [YOLOv6](https://github.com/meituan/YOLOv6), [YOLOv7](https://github.com/WongKinYiu/yolov7), [YOLOv8](https://github.com/ultralytics/ultralytics), [YOLOv9](https://github.com/WongKinYiu/yolov9), [YOLOv10](https://github.com/THU-MIG/yolov10), [YOLO11](https://github.com/ultralytics/ultralytics)
+- **YOLO Models**: [YOLOv5](https://github.com/ultralytics/yolov5), [YOLOv6](https://github.com/meituan/YOLOv6), [YOLOv7](https://github.com/WongKinYiu/yolov7), [YOLOv8](https://github.com/ultralytics/ultralytics), [YOLOv9](https://github.com/WongKinYiu/yolov9), [YOLOv10](https://github.com/THU-MIG/yolov10), [YOLO11](https://github.com/ultralytics/ultralytics), [YOLOv12](https://github.com/sunsmarterjie/yolov12)
 - **SAM Models**: [SAM](https://github.com/facebookresearch/segment-anything), [SAM2](https://github.com/facebookresearch/segment-anything-2), [MobileSAM](https://github.com/ChaoningZhang/MobileSAM), [EdgeSAM](https://github.com/chongzhou96/EdgeSAM), [SAM-HQ](https://github.com/SysCV/sam-hq), [FastSAM](https://github.com/CASIA-IVA-Lab/FastSAM)
 - **Vision Models**: [RT-DETR](https://arxiv.org/abs/2304.08069), [RTMO](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo), [Depth-Anything](https://github.com/LiheYoung/Depth-Anything), [DINOv2](https://github.com/facebookresearch/dinov2), [MODNet](https://github.com/ZHKKKe/MODNet), [Sapiens](https://arxiv.org/abs/2408.12569), [DepthPro](https://github.com/apple/ml-depth-pro), [FastViT](https://github.com/apple/ml-fastvit), [BEiT](https://github.com/microsoft/unilm/tree/master/beit), [MobileOne](https://github.com/apple/ml-mobileone)
 - **Vision-Language Models**: [CLIP](https://github.com/openai/CLIP), [jina-clip-v1](https://huggingface.co/jinaai/jina-clip-v1), [BLIP](https://arxiv.org/abs/2201.12086), [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO), [YOLO-World](https://github.com/AILab-CVC/YOLO-World), [Florence2](https://arxiv.org/abs/2311.06242), [Moondream2](https://github.com/vikhyat/moondream/tree/main)
@@ -57,6 +57,7 @@
 | [YOLOv8<br />YOLO11](https://github.com/ultralytics/ultralytics)                                                  | Object Detection<br />Instance Segmentation<br />Image Classification<br />Oriented Object Detection<br />Keypoint Detection | [demo](examples/yolo)           | ✅     | ✅             | ✅             | ✅                 | ✅                 |
 | [YOLOv9](https://github.com/WongKinYiu/yolov9)                                                                    | Object Detection                                                                                                             | [demo](examples/yolo)           | ✅     | ✅             | ✅             | ✅                 | ✅                 |
 | [YOLOv10](https://github.com/THU-MIG/yolov10)                                                                     | Object Detection                                                                                                             | [demo](examples/yolo)           | ✅     | ✅             | ✅             | ✅                 | ✅                 |
+| [YOLOv12](https://github.com/sunsmarterjie/yolov12)                                                                     | Object Detection                                                                                                             | [demo](examples/yolo)           | ✅     | ✅             | ✅             | ✅                 | ✅                 |
 | [RT-DETR](https://github.com/lyuwenyu/RT-DETR)                                                                    | Object Detection                                                                                                             | [demo](examples/rtdetr)         | ✅     | ✅             | ✅             |                    |                    |
 | [PP-PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.8/configs/picodet)                    | Object Detection                                                                                                             | [demo](examples/picodet-layout) | ✅     | ✅             | ✅             |                    |                    |
 | [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)                                                   | Object Detection                                                                                                             | [demo](examples/picodet-layout) | ✅     | ✅             | ✅             |                    |                    |

diff --git a/src/models/yolo/config.rs b/src/models/yolo/config.rs
@@ -134,6 +134,10 @@ impl Options {
         Self::yolo().with_model_version(11.0.into())
     }
 
+    pub fn yolo_v12() -> Self {
+        Self::yolo().with_model_version(12.0.into())
+    }
+
     pub fn yolo_v8_n() -> Self {
         Self::yolo()
             .with_model_version(8.0.into())

diff --git a/src/models/yolo/impl.rs b/src/models/yolo/impl.rs
@@ -114,9 +114,10 @@ impl YOLO {
                         (Task::ObjectDetection, Version(5, 0) | Version(6, 0) | Version(7, 0)) => {
                             YOLOPredsFormat::n_a_cxcywh_confclss()
                         }
-                        (Task::ObjectDetection, Version(8, 0) | Version(9, 0) | Version(11, 0)) => {
-                            YOLOPredsFormat::n_cxcywh_clss_a()
-                        }
+                        (
+                            Task::ObjectDetection,
+                            Version(8, 0) | Version(9, 0) | Version(11, 0) | Version(12, 0),
+                        ) => YOLOPredsFormat::n_cxcywh_clss_a(),
                         (Task::ObjectDetection, Version(10, 0)) => {
                             YOLOPredsFormat::n_a_xyxy_confcls().apply_nms(false)
                         }
@@ -143,7 +144,7 @@ impl YOLO {
                     let layout = match version {
                         // single task, no need to specified task
                         Version(6, 0) | Version(7, 0) => YOLOPredsFormat::n_a_cxcywh_confclss(),
-                        Version(9, 0) => YOLOPredsFormat::n_cxcywh_clss_a(),
+                        Version(9, 0) | Version(12, 0) => YOLOPredsFormat::n_cxcywh_clss_a(),
                         Version(10, 0) => YOLOPredsFormat::n_a_xyxy_confcls().apply_nms(false),
                         _ => {
                             anyhow::bail!(