Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jahongir7174/yolov8-human
YOLOv8 re-implementation for human detection using PyTorch
https://github.com/jahongir7174/yolov8-human
human-detection object-detection people-detection person-detection python python3 pytorch testing training yolov8
Last synced: about 1 month ago
JSON representation
YOLOv8 re-implementation for human detection using PyTorch
- Host: GitHub
- URL: https://github.com/jahongir7174/yolov8-human
- Owner: jahongir7174
- License: agpl-3.0
- Created: 2023-03-02T05:39:49.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2024-01-11T05:25:23.000Z (12 months ago)
- Last Synced: 2024-01-11T08:25:39.574Z (12 months ago)
- Topics: human-detection, object-detection, people-detection, person-detection, python, python3, pytorch, testing, training, yolov8
- Language: Python
- Homepage:
- Size: 16.2 MB
- Stars: 43
- Watchers: 3
- Forks: 3
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
YOLOv8 re-implementation for person detection 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 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 | COCO weights | CrowdHuman weights |
|:-------:|------------------------------------------------------------------------------------------:|---------------------------:|
| v8_n | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_n.pt) | [model](./weights/best.pt) |
| v8_s | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_s.pt) | - |
| v8_m | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_m.pt) | - |
| v8_l | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_l.pt) | - |
| v8_x | [model](https://github.com/jahongir7174/YOLOv8-pt/releases/download/v0.0.1-alpha/v8_x.pt) | - |
* the weights are ported from original repo, see reference
### Dataset structure
├── Person
├── images
├── train2017
├── 1111.jpg
├── 2222.jpg
├── val2017
├── 1111.jpg
├── 2222.jpg
├── labels
├── train2017
├── 1111.txt
├── 2222.txt
├── val2017
├── 1111.txt
├── 2222.txt
* Public person detection datasets
* [COCO](https://cocodataset.org/#home)
* [CrowdHuman](https://www.crowdhuman.org/download.html)
* [HIEVE](http://humaninevents.org/data.html?title=1)
* [VisDrone](https://github.com/VisDrone/VisDrone-Dataset)
* [VFP290K](https://sites.google.com/view/dash-vfp300k/)
* [Argoverse](https://eval.ai/web/challenges/challenge-page/800/overview)
* [CEPDOF](https://vip.bu.edu/projects/vsns/cossy/datasets/cepdof/)
* [HABBOF](https://vip.bu.edu/projects/vsns/cossy/datasets/habbof/)
* [MW-R](https://vip.bu.edu/projects/vsns/cossy/datasets/mw-r/)
* [TIDOS](https://vip.bu.edu/projects/vsns/cossy/datasets/tidos/)
* [WEPDTOF](https://vip.bu.edu/projects/vsns/cossy/datasets/wepdtof/)
* [DEPOF](https://vip.bu.edu/projects/vsns/cossy/datasets/depof/)
* [FRIDA](https://vip.bu.edu/projects/vsns/cossy/datasets/frida/)
#### Reference
* https://github.com/ultralytics/yolov5
* https://github.com/ultralytics/ultralytics
* https://github.com/open-mmlab/mmyolo