π Introduction
This directory is part of the innovative work developed by Ultralytics and is available for use and redistribution under the AGPL-3.0 license. For an insightful overview of our diverse projects, we invite you to visit Ultralytics.
π Description
The Ultralytics WAVE repository offers leading-edge WAveform Vector Exploitation code. This novel approach to particle physics detector readout and reconstruction leverages Machine Learning and Deep Neural Networks to enhance data analysis and interpretation.
π¦ Requirements
To dive into WAVE, ensure you have Python 3.7 or newer. Necessary libraries can be installed via pip
using the provided requirements.txt
with the following command:
pip3 install -U -r requirements.txt
The essential packages required are:
numpy
: For numerical computing.scipy
: For scientific and technical computing.torch
(version 0.4.0 or higher): For constructing and training neural networks.tensorflow
(version 1.8.0 or higher): Provides a comprehensive, flexible ecosystem of tools, libraries, and community resources.plotly
: Optional for creating interactive plots.
π Running
To execute WAVE models, you have several scripts at your disposal:
- PyTorch Implementation: Utilize
wave_pytorch.py
for models based on the PyTorch framework. - TensorFlow Implementation: Call upon
wave_tf.py
for TensorFlow-based models. - PyTorch on Google Cloud Platform: Deploy
wave_pytorch_gcp.py
within the Google Cloud Platform ecosystem.
Visualizations
Below are example visualizations of waveforms and training processes:
π Citation
If you find this project useful in your research or wish to reference it, please consider citing our publication:
Jocher, G., Nishimura, K., Koblanski, J. and Li, V. (2018). WAVE: Machine Learning for Full-Waveform Time-Of-Flight Detectors. ArXiv.org. Available at: https://arxiv.org/abs/1811.05875.
π€ Contribute
We welcome contributions from the community! Whether you're fixing bugs, adding new features, or improving documentation, your input is invaluable. Take a look at our Contributing Guide to get started. Also, we'd love to hear about your experience with Ultralytics products. Please consider filling out our Survey. A huge π and thank you to all of our contributors!
Β©οΈ License
Ultralytics is excited to offer two different licensing options to meet your needs:
- AGPL-3.0 License: Perfect for students and hobbyists, this OSI-approved open-source license encourages collaborative learning and knowledge sharing. Please refer to the LICENSE file for detailed terms.
- Enterprise License: Ideal for commercial use, this license allows for the integration of Ultralytics software and AI models into commercial products without the open-source requirements of AGPL-3.0. For use cases that involve commercial applications, please contact us via Ultralytics Licensing.
π¬ Contact Us
For bug reports, feature requests, and contributions, head to GitHub Issues. For questions and discussions about this project and other Ultralytics endeavors, join us on Discord!