The SparseTensors implemented in NGF/sparse.py are very well suited for the molecule data structures/distributions used in these repo. An advantage of the SparseTensors tensors is that they do not require padding.
It would be easy to implement an append or an extend method to merge the tensors. This would significantly speed up the preprocessing for larger datasets, and obsolete the padaxis and concat_mol_tensors functions.
The
SparseTensor
s implemented in NGF/sparse.py are very well suited for the molecule data structures/distributions used in these repo. An advantage of the SparseTensors tensors is that they do not require padding.It would be easy to implement an
append
or anextend
method to merge the tensors. This would significantly speed up the preprocessing for larger datasets, and obsolete thepadaxis
andconcat_mol_tensors
functions.