Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/jahongir7174/yolov8-pose

YOLOv8-pose implementation using PyTorch
https://github.com/jahongir7174/yolov8-pose

detection human-pose-estimation opencv opencv-python pose-estimation python pytorch yolopose yolov8

Last synced: about 2 hours ago
JSON representation

YOLOv8-pose implementation using PyTorch

Host: GitHub
URL: https://github.com/jahongir7174/yolov8-pose
Owner: jahongir7174
License: agpl-3.0
Created: 2023-04-06T04:35:51.000Z (over 1 year ago)
Default Branch: master
Last Pushed: 2023-09-27T02:47:45.000Z (about 1 year ago)
Last Synced: 2023-09-27T12:37:17.856Z (about 1 year ago)
Topics: detection, human-pose-estimation, opencv, opencv-python, pose-estimation, python, pytorch, yolopose, yolov8
Language: Python
Homepage:
Size: 43.5 MB
Stars: 24
Watchers: 2
Forks: 5
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        YOLOv8-pose re-implementation using PyTorch

### Installation

```

conda create -n YOLO python=3.8

conda activate YOLO

conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch-lts

pip install opencv-python==4.5.5.64

pip install PyYAML

pip install tqdm

```

### Train

* Configure your pose dataset path in `main.py` for training

* Run `bash main.sh $ --train` for training, `$` is number of GPUs

### Test

* Configure your dataset path in `main.py` for testing

* Run `python main.py --test` for testing

### Results

|  Version   | Epochs | Pose mAP |                                                                                       Download |

|:----------:|:------:|---------:|-----------------------------------------------------------------------------------------------:|

| v8_n_pose  |  1000  |     50.2 |                                                                     [model](./weights/best.pt) |

| v8_n_pose* |  1000  |     50.5 | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_n_pose.pt) |

| v8_s_pose* |  1000  |     59.5 | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_s_pose.pt) |

| v8_m_pose* |  1000  |     63.8 | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_m_pose.pt) |

| v8_l_pose* |  1000  |     67.4 | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_l_pose.pt) |

| v8_x_pose* |  1000  |     69.4 | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_x_pose.pt) |

* `*` means that weights are ported from original repo, see reference

### Dataset structure

    ├── COCO 

        ├── images

            ├── train2017

                ├── 1111.jpg

                ├── 2222.jpg

            ├── val2017

                ├── 1111.jpg

                ├── 2222.jpg

        ├── labels

            ├── train2017

                ├── 1111.txt

                ├── 2222.txt

            ├── val2017

                ├── 1111.txt

                ├── 2222.txt

### Results

![Alt Text](./demo/demo.gif)

#### Reference

* https://github.com/ultralytics/yolov5

* https://github.com/ultralytics/ultralytics