Datasets and models for wildfire detection in PyTorch
Pyrovision: wildfire early detection
The increasing adoption of mobile phones have significantly shortened the time required for firefighting agents to be alerted of a starting wildfire. In less dense areas, limiting and minimizing this duration remains critical to preserve forest areas.
Pyrovision aims at providing the means to create a wildfire early detection system with state-of-the-art performances at minimal deployment costs.
Table of Contents
- Getting Started
- Python 3.6 (or more recent)
You can install the latest release of the package using pypi as follows:
pip install pyrovision
or conda as follows:
conda install -c pyronear pyrovision
You can use the library like any other python package to detect wildfires as follows:
from pyrovision.datasets import OpenFire dataset = OpenFire('./data', download=True)
If you wish to deploy containerized environments, a Dockerfile is provided for you build a docker image:
docker build . -t <YOUR_IMAGE_TAG>
You are free to use any training script, but some are already provided for reference. In order to use them, install the specific requirements and check script options as follows:
pip install -r references/requirements.txt python references/classification/train.py --help
You can then use the script to train tour model on one of our datasets:
Download Dataset from https://drive.google.com/file/d/1Y5IyBLA5xDMS1rBdVs-hsVNGQF3djaR1/view?usp=sharing
This dataset is protected by a password, please contact us at email@example.com
python train.py WildFireLght/ --model rexnet1_0x --lr 1e-3 -b 16 --epochs 20 --opt radam --sched onecycle --device 0
You can also use out opensource dataset without password
python train.py OpenFire/ --use-openfire --model rexnet1_0x --lr 1e-3 -b 16 --epochs 20 --opt radam --sched onecycle --device 0
Please refer to
CONTRIBUTING if you wish to contribute to this project.
This project is developed and maintained by the repo owner and volunteers from Data for Good.
Distributed under the AGPLv3 License. See
LICENSE for more information.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size pyrovision-0.1.2-py3-none-any.whl (43.0 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
Hashes for pyrovision-0.1.2-py3-none-any.whl