GLambard / SMILES-X

Autonomous characterization of molecular compounds from small datasets without descriptors
MIT License
43 stars 13 forks source link

Vocabulary bug fix #6

Closed egracheva closed 4 years ago

egracheva commented 4 years ago

The set() command would create a different vocabulary every time the kernel is relaunched. It made impossible to continue training or to make predictions from within the main.py. Now the bug is fixed. As the vocabulary is the same for all the folds, the naming has been changed over all the files using vocabulary file.