Modification of original MolGAN: An implicit generative model for small molecular graphs (https://arxiv.org/abs/1805.11973)
- python>=3.7
- tensorflow>=1.7.0: https://tensorflow.org
- rdkit: https://www.rdkit.org
- numpy
- scikit-learn
- Modify hyperparameters in the
main
function ofexample.py
- To train:
- Set
skip_training
toFalse
- Set
- To test:
- Keep hyperparameters unchanged
- Set
skip_training
toTrue
- Set
test_epoch
to the epoch used for inference
Then, type
python example.py
to run.
Figures of generated molecules are saved as a png file in a folder whose name begins with qm9_5k..., which is records the experiment setting.