|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- object-detection |
|
|
- vision |
|
|
- yolov8 |
|
|
- sports |
|
|
- football |
|
|
- tennis |
|
|
library_name: ultralytics |
|
|
pipeline_tag: object-detection |
|
|
--- |
|
|
|
|
|
# ⚽ Football & Sports Player Detection (YOLOv8) |
|
|
|
|
|
This model is a fine-tuned version of **YOLOv8 Nano**, designed to detect players, balls, and sports equipment in match footage (Football/Tennis). |
|
|
|
|
|
It was developed specifically to demonstrate **Data Engineering** techniques, achieving high generalization performance even when trained on a **restricted dataset** through the use of aggressive offline and online Data Augmentation strategies. |
|
|
|
|
|
## 🏷️ Classes |
|
|
The model is trained to detect the following 3 classes: |
|
|
* `0`: **Person** (Players) |
|
|
* `1`: **Ball** (Football, Tennis ball) |
|
|
* `2`: **Equipment** (Rackets) |
|
|
|
|
|
## 💻 How to Use |
|
|
|
|
|
To use this model in your Python project, you need the `ultralytics` and `huggingface_hub` libraries. |
|
|
|
|
|
### Installation |
|
|
```bash |
|
|
pip install ultralytics huggingface_hub |
