CFGAN is a Python library for advanced image processing tasks leveraging Conditional Generative Adversarial Networks (cGANs). The library is designed for applications such as image denoising, super-resolution reconstruction, and localization tasks in microscopy and other imaging domains.
- U-Net Generator: Advanced encoder-decoder architecture with skip connections for high-quality image generation
- CNN Discriminator: Deep convolutional discriminator for effective real/fake classification
- Comprehensive Training Pipeline: Complete framework for model training, evaluation, and monitoring
- Image Processing Toolkit: Utilities for image manipulation, analysis, and visualization
- Flexible Configuration System: YAML-based configuration for model parameters and training settings
- Python 3.10 or higher
- PyTorch 2.5.1 or higher
- NumPy 2.0.0 or higher
- Other dependencies listed in
requirements.txt
-
Clone the repository:
git clone https://github.com/zhoux77899/CFGAN.git cd CFGAN -
Install the package in development mode:
pip install -e . -
Install the required dependencies:
pip install -r requirements.txt
Contributions to CFGAN are welcome! Here are some ways you can contribute:
- Report Issues: Submit bug reports and feature requests through the GitHub issue tracker.
- Submit Pull Requests: Contribute code fixes, improvements, or new features.
- Improve Documentation: Help enhance the project documentation and examples.
Before contributing, please ensure that your code adheres to the project's coding standards and passes all tests.
This project is licensed under the MIT License.
For questions or inquiries about the project, please contact:
- Author: zhoux77899
- GitHub: https://github.com/zhoux77899/CFGAN