Skip to content

2.1.0

Compare
Choose a tag to compare
@tjkessler tjkessler released this 01 Apr 01:44
· 41 commits to master since this release
6ce9949
  • New method for atom/bond tokenizing (integer tokens, passed through torch.nn.Embedding layer at start of model)
  • Removed GRU and scatter add functions, leads to faster and more accurate results
  • Changed MFConv to GeneralConv (GeneralConv considers both atom and bond features during its message passing step)
    • General flow for each message passing step is:
      • embedded_bonds -> EdgeConv -> updated embedded_bonds
      • embedded_atoms + embedded_bonds -> GeneralConv -> updated embedded_atoms
    • Separate edge/node convolutions, where node convolutions also account for updated edge states, is used effectively by Jørgensen et al. (paper)
  • Updated/added examples