@ -191,17 +191,15 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
See [Obb Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes.
<!-- TODO: should we report multi-scale results only as they're better or both multi-scale and single-scale. -->
- **mAP<sup>val</sup>** values are for single-model single-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0`
- **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test`
- **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
@ -115,13 +115,13 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
See [Oriented Detection Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes.
@ -4,7 +4,7 @@ description: Learn how to use oriented object detection models with Ultralytics
keywords: yolov8, oriented object detection, Ultralytics, DOTA dataset, rotated object detection, object detection, model training, model validation, image prediction, model export
---
# Oriented Object Detection
# Oriented Bounding Boxes Object Detection
<!-- obb task poster -->
@ -24,17 +24,15 @@ YOLOv8 pretrained Obb models are shown here, which are pretrained on the [DOTAv1
[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use.
<!-- TODO: should we report multi-scale results only as they're better or both multi-scale and single-scale. -->
- **mAP<sup>val</sup>** values are for single-model single-scale on [DOTAv1 test](http://cocodataset.org) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0`
- **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1 test](http://cocodataset.org) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test`
- **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX Runtime and OpenCV's API.
@ -11,7 +10,7 @@ This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX
- Faster than OpenCV's DNN inference on both CPU and GPU.
- Supports FP32 and FP16 CUDA acceleration.
## Note :coffee:
## Note ☕
1. Benefit for Ultralytics' latest release, a `Transpose` op is added to the YOLOv8 model, while make v8 and v5 has the same output shape. Therefore, you can run inference with YOLOv5/v7/v8 via this project.
Laughing
1 year ago
committed by
GitHub