Published January 7, 2020
| Version 0.0.5
Software
Open
muammar/ml4chem: 0.0.5
Creators
Description
- New
to_pandas()
method to convert features to DataFrame. - Print date where a module was accessed.
- New base classes that can be used to build new features and model modules.
- New
Annealer()
class for training VAEs. Right now it is hardcoded in the VAE class but will be improved later. - Addition of
MultiStepLR
andStepLR
learning rate schedulers. - ml4chem.data.visualization: Added kwargs to plot_atomic_features()
- Improved memory usage of Gaussian() at "training", and fixed KernelRidge.
- A
batch_size
keyword argument can be passed to thePotentials.load()
function so that we can do predictions of trajectory files instead of Atoms().
Files
muammar/ml4chem-0.0.5.zip
Files
(1.5 MB)
Name | Size | Download all |
---|---|---|
md5:51b7b7c9ac9a921fbfb5257108936494
|
1.5 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/muammar/ml4chem/tree/0.0.5 (URL)