|
|
--- |
|
|
license: agpl-3.0 |
|
|
datasets: |
|
|
- ds4sd/DocLayNet |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
- mape |
|
|
- precision |
|
|
- recall |
|
|
pipeline_tag: object-detection |
|
|
--- |
|
|
|
|
|
🤗 Live Demo here: [https://huggingface.co/spaces/omoured/YOLOv10-Document-Layout-Analysis](https://huggingface.co/spaces/omoured/YOLOv10-Document-Layout-Analysis) |
|
|
|
|
|
<!-- ABOUT THE PROJECT --> |
|
|
## About 📋 |
|
|
|
|
|
The models were fine-tuned using 4xA100 GPUs on the Doclaynet-base dataset, which consists of 6910 training images, 648 validation images, and 499 test images. |
|
|
|
|
|
<p align="center"> |
|
|
<img src="https://github.com/moured/YOLOv10-Document-Layout-Analysis/raw/main/images/samples.gif" height="320"/> |
|
|
</p> |
|
|
|
|
|
## Results 📊 |
|
|
| Model | mAP50 | mAP50-95 | Model Weights | |
|
|
|---------|-------|----------|---------------| |
|
|
| YOLOv10-x | 0.924 | 0.740 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10x_best.pt) | |
|
|
| YOLOv10-b | 0.922 | 0.732 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10b_best.pt) | |
|
|
| YOLOv10-l | 0.921 | 0.732 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10l_best.pt) | |
|
|
| YOLOv10-m | 0.917 | 0.737 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10m_best.pt) | |
|
|
| YOLOv10-s | 0.905 | 0.713 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10s_best.pt) | |
|
|
| YOLOv10-n | 0.892 | 0.685 | [Download](https://github.com/moured/YOLOv10-Document-Layout-Analysis/releases/download/doclaynet_weights/yolov10n_best.pt) | |
|
|
|
|
|
## Codes 🔥 |
|
|
|
|
|
Check out our Github repo for inference codes: [https://github.com/moured/YOLOv10-Document-Layout-Analysis](https://github.com/moured/YOLOv10-Document-Layout-Analysis) |
|
|
|
|
|
## References 📝 |
|
|
|
|
|
1. YOLOv10 |
|
|
``` |
|
|
BibTeX |
|
|
@article{wang2024yolov10, |
|
|
title={YOLOv10: Real-Time End-to-End Object Detection}, |
|
|
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang}, |
|
|
journal={arXiv preprint arXiv:2405.14458}, |
|
|
year={2024} |
|
|
} |
|
|
``` |
|
|
|
|
|
|
|
|
2. DocLayNet |
|
|
``` |
|
|
@article{doclaynet2022, |
|
|
title = {DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis}, |
|
|
doi = {10.1145/3534678.353904}, |
|
|
url = {https://arxiv.org/abs/2206.01062}, |
|
|
author = {Pfitzmann, Birgit and Auer, Christoph and Dolfi, Michele and Nassar, Ahmed S and Staar, Peter W J}, |
|
|
year = {2022} |
|
|
} |
|
|
``` |
|
|
|
|
|
## Contact |
|
|
LinkedIn: [https://www.linkedin.com/in/omar-moured/](https://www.linkedin.com/in/omar-moured/) |
