Closed sgbaird closed 3 years ago
Seems that it may have been a pytorch version incompatibility. Will probably put in a pull request once I polish the .ipynb up a bit.
The CGCNN featurizer is incredibly difficult to use. We may add a new module with things better thought out for using graphnet models. Stay tuned on the main repo for progress on that front!
I've been struggling a lot with getting CGCNNFeaturizer to work. The google groups doesn't seem to have much discussion on this, nor does the CGCNN repo have much to say about it other than a clarification about python bindings. The matminer documentation is also a bit hard to follow, but I think I've understood the main components. Does someone have (or could someone put together) a basic .ipynb showing how to get features from one of the pretrained models (e.g. 'bulk-moduli)?