diff --git a/README.md b/README.md index 6f985dde3a..ceacbe51ca 100644 --- a/README.md +++ b/README.md @@ -46,11 +46,15 @@ ________________________________________________________________________________ ### Ready to deploy pre-trained SOTA models -YOLO-NAS architecture is out! The new YOLO-NAS delivers state-of-the-art performance with the unparalleled accuracy-speed performance, outperforming other models such as YOLOv5, YOLOv6, YOLOv7 and YOLOv8. -Check it out here: [YOLO-NAS](YOLONAS.md). +YOLO-NAS and YOLO-NAS-POSE architectures are out! +The new YOLO-NAS delivers state-of-the-art performance with the unparalleled accuracy-speed performance, outperforming other models such as YOLOv5, YOLOv6, YOLOv7 and YOLOv8. +A YOLO-NAS-POSE model for pose estimation is also available, delivering state-of-the-art accuracy/performance tradeoff. + +Check these out here: [YOLO-NAS](YOLONAS.md) & [YOLO-NAS-POSE](YOLONAS-POSE.md).
- + +
```python @@ -77,6 +81,11 @@ model = models.get(Models.YOLO_NAS_M, pretrained_weights="coco") +#### Pose Estimation +
+ + +
### Easy to train SOTA Models @@ -123,6 +132,13 @@ pip install super-gradients ## What's New +__________________________________________________________________________________________________________ +Version 3.4.0 (November 6, 2023) + +* [YoloNAS-Pose](YOLONAS-POSE.md) model released - a new frontier in pose estimation +* Added option to export a recipe to a single YAML file or to a standalone train.py file +* Other bugfixes & minor improvements. Full release notes available [here](https://github.com/Deci-AI/super-gradients/releases/tag/3.4.0) + __________________________________________________________________________________________________________ Version 3.1.3 (July 19, 2023) @@ -148,16 +164,6 @@ Version 3.1.1 (May 3rd) Check out SG full [release notes](https://github.com/Deci-AI/super-gradients/releases). -## Coming soon -__________________________________________________________________________________________________________ -- [ ] Pre-trained pose estimation model -- [ ] Test Time Augmentations (TTA) -- [ ] Recipe to train DEKR model(convertable to TRT) -- [ ] Key-points Rescoring for Pose estimation -- [ ] LR finder -- [ ] Data analysis tools - - ## Table of Content __________________________________________________________________________________________________________ diff --git a/documentation/source/images/yolo_nas_pose_frontier_t4.png b/documentation/source/images/yolo_nas_pose_frontier_t4.png index fcfc445963..01471606a8 100644 Binary files a/documentation/source/images/yolo_nas_pose_frontier_t4.png and b/documentation/source/images/yolo_nas_pose_frontier_t4.png differ diff --git a/documentation/source/images/yolo_nas_pose_frontier_xavier_nx.png b/documentation/source/images/yolo_nas_pose_frontier_xavier_nx.png new file mode 100644 index 0000000000..15656e6376 Binary files /dev/null and b/documentation/source/images/yolo_nas_pose_frontier_xavier_nx.png differ diff --git a/documentation/source/welcome.md b/documentation/source/welcome.md index 131c7ea118..bb67a68520 100644 --- a/documentation/source/welcome.md +++ b/documentation/source/welcome.md @@ -32,29 +32,15 @@ Check out our [Quickstart tutorial](QuickstartBasicToolkit.md) to get learn the You can also start from our tutorial on [Detection](ObjectDetection.md), [Segmentation](Segmentation.md) or [Pose Estimation](PoseEstimation.md). -## What's New (v3.1.0) -__________________________________________________________________________________________________________ - -* [YOLO-NAS](https://bit.ly/41WeNPZ) -* New [predict function](https://bit.ly/3oZfaea) (predict on any image, video, url, path, stream) -* [RoboFlow100](https://bit.ly/40YOJ5z) datasets integration -* A new [Documentation Hub](https://docs.deci.ai/super-gradients/documentation/source/welcome.html) -* Integration with [DagsHub for experiment monitoring](https://bit.ly/3ALFUkQ) -* Support [Darknet/Yolo format detection dataset](https://bit.ly/41VX6Qu) (used by Yolo v5, v6, v7, v8) -* [Segformer](https://bit.ly/3oYu6Jp) model and recipe -* Post Training Quantization and Quantization Aware Training - [notebooks](http://bit.ly/3KrN6an) +## What's New -Check out SG full [release notes](https://github.com/Deci-AI/super-gradients/releases). - -## Coming soon __________________________________________________________________________________________________________ +Version 3.4.0 (November 6, 2023) + +* [YoloNAS-Pose](YOLONAS-POSE.md) model released - a new frontier in pose estimation +* Added option to export a recipe to a single YAML file or to a standalone train.py file +* Other bugfixes & minor improvements. Full release notes available [here](https://github.com/Deci-AI/super-gradients/releases/tag/3.4.0) -- [ ] Pre-trained pose estimation model -- [ ] Test Time Augmentations (TTA) -- [ ] Recipe to train DEKR model(convertable to TRT) -- [ ] Key-points Rescoring for Pose estimation -- [ ] LR finder -- [ ] Data analysis tools ## Citation If you are using SuperGradients library in your research, please cite SuperGradients deep learning training library.