|
|
--- |
|
|
title: Submission Template |
|
|
emoji: 🔥 |
|
|
colorFrom: yellow |
|
|
colorTo: green |
|
|
sdk: docker |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
|
|
|
# Smoke fire detection |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This is a yolo-based model for the Frugal AI Challenge 2025, specifically for the wildfire smoke detection |
|
|
### Intended Use |
|
|
|
|
|
- **Primary intended uses**: Detect fire smoke on photos of forests, in different natural settings |
|
|
- **Primary intended users**: Researchers and developers participating in the Frugal AI Challenge |
|
|
- **Out-of-scope use cases**: Not intended for production use or real-world classification tasks |
|
|
|
|
|
## Training Data |
|
|
|
|
|
The model uses the pyronear/pyro-sdis dataset: |
|
|
- Size: ~33 600 examples |
|
|
- Split: 88% train, 12% test |
|
|
|
|
|
### Labels |
|
|
0. Smoke |
|
|
|
|
|
## Performance |
|
|
|
|
|
### Metrics |
|
|
- **Accuracy**: ~92 |
|
|
- **Environmental Impact**: |
|
|
- Emissions tracked in gCO2eq 0.23 |
|
|
- Energy consumption tracked in Wh 3.5 |
|
|
|
|
|
### Model Architecture |
|
|
YOLO 11 |
|
|
|
|
|
## Environmental Impact |
|
|
|
|
|
Environmental impact is tracked using CodeCarbon, measuring: |
|
|
- Carbon emissions during inference |
|
|
- Energy consumption during inference |
|
|
|
|
|
This tracking helps establish a baseline for the environmental impact of model deployment and inference. |
|
|
|
|
|
## Limitations |
|
|
- May require GPU |
|
|
|
|
|
## Ethical Considerations |
|
|
- Environmental impact is tracked to promote awareness of AI's carbon footprint |
|
|
``` |
|
|
|
