metadata

title: Submission Template
emoji: 🔥
colorFrom: yellow
colorTo: green
sdk: docker
pinned: false

Object Detector for forest fire smoke

Model Description

This is a frugal object detector use to detect fire smoke, as part of the Frugal AI Challenge 2024. It is based of the yolo model series

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

Training Data

The model uses the pyronear/pyro-sdis dataset:

Size: ~33 600 examples
Split: 88% train, 12% test
Images with smoke or no smoke

Labels

Smoke

Performance

Metrics

All reported on the test set

Accuracy: ~ 90.8%
Precision: ~ 91.7%
Recall: ~ 97.8%
Environmental Impact:
- Emissions tracked in gCO2eq: 0.205
- Energy consumption tracked in Wh: 3.66

Model Architecture

Based of YOLOv11, see https://arxiv.org/abs/2410.17725, fine tuned on the pyronear dataset. The network is pruned and quantized to be as compressed as possible.

Inference should ideally performed on GPU - the speed bump is drastic, it is more energy efficient than CPU inference which takes much longer.

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

Quantization was performed to FP16 - INT8 could compress even more but the accuracy drop was too big. Finding a way to smartly quantize and calibrate to INT8 could be interesting
To maximize inference speed even more, the model can be converted to TensorRT - it is note done in this repository, as the same type of GPU needs to be used both for exporting to TensorRT and inferencing with TensorRT

Ethical Considerations

Environmental impact is tracked to promote awareness of AI's carbon footprint