README.md
| 1 | --- |
| 2 | license: agpl-3.0 |
| 3 | tags: |
| 4 | - object-detection |
| 5 | - computer-vision |
| 6 | - yolov10 |
| 7 | - pytorch_model_hub_mixin |
| 8 | datasets: |
| 9 | - detection-datasets/coco |
| 10 | library_name: yolov10 |
| 11 | inference: false |
| 12 | --- |
| 13 | |
| 14 | ### Model Description |
| 15 | [YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1) |
| 16 | |
| 17 | - arXiv: https://arxiv.org/abs/2405.14458v1 |
| 18 | - github: https://github.com/THU-MIG/yolov10 |
| 19 | |
| 20 | ### Installation |
| 21 | ``` |
| 22 | pip install git+https://github.com/THU-MIG/yolov10.git |
| 23 | ``` |
| 24 | |
| 25 | ### Training and validation |
| 26 | ```python |
| 27 | from ultralytics import YOLOv10 |
| 28 | |
| 29 | model = YOLOv10.from_pretrained('jameslahm/yolov10s') |
| 30 | # Training |
| 31 | model.train(...) |
| 32 | # after training, one can push to the hub |
| 33 | model.push_to_hub("your-hf-username/yolov10-finetuned") |
| 34 | |
| 35 | # Validation |
| 36 | model.val(...) |
| 37 | ``` |
| 38 | |
| 39 | ### Inference |
| 40 | |
| 41 | Here's an end-to-end example showcasing inference on a cats image: |
| 42 | |
| 43 | ```python |
| 44 | from ultralytics import YOLOv10 |
| 45 | |
| 46 | model = YOLOv10.from_pretrained('jameslahm/yolov10s') |
| 47 | source = 'http://images.cocodataset.org/val2017/000000039769.jpg' |
| 48 | model.predict(source=source, save=True) |
| 49 | ``` |
| 50 | which shows: |
| 51 | |
| 52 |  |
| 53 | |
| 54 | ### BibTeX Entry and Citation Info |
| 55 | ``` |
| 56 | @article{wang2024yolov10, |
| 57 | title={YOLOv10: Real-Time End-to-End Object Detection}, |
| 58 | author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang}, |
| 59 | journal={arXiv preprint arXiv:2405.14458}, |
| 60 | year={2024} |
| 61 | } |
| 62 | ``` |