Trained 1CH VAE model from 6/8/24
Code available at https://github.com/sandialabs/pvcracks/
- This VAE model is for the one channel version, it only uses the crack masks of the Electroluminescence images.
- The purpose is to parametrize the crack masks and compress the information into latent vectors.
- Latent space visualization can be used to cluster the images in categories according to severity of damage.
- Visualization can also be used to generate new crack masks within a certain cluster.
- Latent vectors can also be used to correlate to power loss using the additional model in the pvcracks repo.
There are no views created for this resource yet.
Resource Metadata
| data quality | Good |
|---|---|
| data type | Other |
| instrument | SNL |
| size | 290 MiB |
| Last updated | July 4, 2024 |
|---|---|
| Created | July 4, 2024 |
| Format | pth |
| License | No License Provided |