This dataset and code are presented in the paper: Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
Please cite our paper if you use this repo. Thanks!
Regenwetter, L., Srivastava, A., Gutfreund, D., & Ahmed, F. (2023). Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design. arXiv preprint arXiv:2302.02913.
Also check out the Project page.
This repo contains implementations for:
- 20 evaluation metrics
- 20 dataset constructors, objective functions, and constraint functions
- Generative Adversarial Network and Conditional GAN
- Variational Autoencoder and Conditional VAE
- Multi-Objective Pefromance-Aware Diverse GAN
- Design Target Achievement Index GAN
- Plotting distribution matching, constraint satisfaction, and performance achievement problems on 2D data
The following packages are needed:
- Tensorflow
- Matplotlib
- Pymoo
- Imageio
- Pandas
- Scikit-learn
- Openpyxl