Dataset
Tutorial for conditional generative adversarial network
This tutorial aims to give an introduction of how to use a deep generative model, conditional generative adversarial network (CGAN). The CGAN can be used for the inverse design of 2D and 3D microstructures with target properties. The CGAN is trained with supervised learning using a labeled dataset. The dataset consists of a large number of geometries and their corresponding properties (e.g., elastic moduli). After training, the CGAN can generate a batch of geometries using target properties at inputs. In our previous two papers, we have demonstrated how to use the CGAN for the inverse design of 2D auxetic metamaterials and 3D architected materials. We hope this tutorial can be useful for those who are interested in the inverse design problems of microstructures.
- DOI
- First published at
- Creator
- Keyword
- Resource type
- Data origin
- Publisher
- Date published
- 04/01/2023
- Rights statement
- Journal
- Funding reference
Items
| Thumbnail | Title | Date Uploaded | Size | Visibility | Actions |
|---|---|---|---|---|---|
|
CGAN_main.py | 14.1 KB | MDR Open |
|
|
|
|
generate_geometies_using_trained_cgan.py | 5.94 KB | MDR Open |
|
|
|
|
readme.pdf | 486 KB | MDR Open |
|
|
|
|
solver.py | 8.71 KB | MDR Open |
|