PyroNear Logo

CI Status Documentation Status Test coverage percentage black

PyPi Status Anaconda Docker Image Version pyversions license

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.

You can use the library like any other python package to detect wildfires as follows:

from pyrovision.models import rexnet1_0x
from torchvision import transforms
import torch
from PIL import Image
# Init
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
tf = transforms.Compose([transforms.Resize(size=(448)), transforms.CenterCrop(size=448),
 transforms.ToTensor(), normalize])
model = rexnet1_0x(pretrained=True).eval()
# Predict
im = tf(Image.open("path/to/your/image.jpg").convert('RGB'))
with torch.no_grad():
 pred = model(im.unsqueeze(0))
 is_wildfire = torch.sigmoid(pred).item() >= 0.5

Python 3.6 (or higher) and pip/conda are required to install PyroVision.

You can install the last stable release of the package using pypi as follows:

pip install pyrovision

or using conda:

conda install -c pyronear pyrovision

Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source:

git clone https://github.com/pyronear/pyro-vision.git
pip install -e pyro-vision/.

The full package documentation is available here for detailed specifications.

The project includes a minimal demo app using Gradio

demo_app

You can check the live demo, hosted on 🤗 HuggingFace Spaces 🤗 over here 👇 Hugging Face Spaces

If you wish to deploy containerized environments, a Dockerfile is provided for you build a docker image:

docker build . -t <YOUR_IMAGE_TAG>

Looking for a boilerplate to deploy a model from PyroVision with a REST API? Thanks to the wonderful FastAPI framework, you can do this easily. Follow the instructions in ./api to get your own API running!

If you wish to train models on your own, we provide training scripts for multiple tasks! Please refer to the ./references folder if that's the case.

If you wish to cite this project, feel free to use this BibTeX reference:

@misc{pyrovision2019,
 title={Pyrovision: wildfire early detection},
 author={Pyronear contributors},
 year={2019},
 month={October},
 publisher = {GitHub},
 howpublished = {\url{https://github.com/pyronear/pyro-vision}}
}

Please refer to CONTRIBUTING to help grow this project!

Distributed under the Apache 2 License. See LICENSE for more information.