fire-detection-from-images, this project use Yolov5 network to detect fire in images, it is implemented by PyTorch.
The effect of this project
The effect looks like:
We can find the probability of fire in a image.
Dataset for this project
This project has used 1155 images from FireNET datase. You can find these images in here.
The performance of detecting fire
By experiment, the performance is: Precision of 0.6, Recall of 0.7, trained on 1155 images (337 base images + augmentation)
How to use?
You can run code below to test this project.
python3 -m venv venv source venv/bin/activate pip3 install -r requirements.txt python3 demo.py
You also can download this project source code in here: fire-detection-from-images source code download