DeepQMC implements variational quantum Monte Carlo for electrons in molecules, using deep neural networks written in PyTorch as trial wave functions. Besides the core functionality, it contains implementations of the following ansatzes:
- PauliNet [video]: https://arxiv.org/abs/1909.08423
Install and update using Pip.
pip install -U deepqmc[wf,train]
>>> from deepqmc import Molecule, evaluate, train
>>> from deepqmc.wf import PauliNet
>>> mol = Molecule.from_name('LiH')
>>> net = PauliNet.from_hf(mol).cuda()
converged SCF energy = -7.9846409186467
>>> train(net)
equilibrating: 64it [00:08, 7.58it/s]
training: 0%| | 46/10000 [01:37<5:50:59, 2.12s/it, E=-8.0371(24)]
KeyboardInterrupt
>>> evaluate(net)
evaluating: 23%|▋ | 134/571 [01:08<03:44, 1.94it/s, E=-8.0455(32)]- Documentation: https://deepqmc.github.io