This is a P.S. not a real issue. https://github.com/deepchem/deepchem/pull/1182 in case you want to look at the implementation. It uses tf.losses.hingeloss instead of your shifted relu, which doesn't force differentiation space between a pair of molecules.
This is a P.S. not a real issue.
deepchem/deepchem#1182 in case you want to look at the implementation.
It uses tf.losses.hingeloss instead of your shifted relu, which doesn't force differentiation space between a pair of molecules.