torchmd/torchmd-net
Neural network potential models (TensorNet, Transformers, GNN) for molecular dynamics simulation implemented in PyTorch.
Not currently ranked — collecting fresh signals.
star history
TorchMD-NET provides neural network architectures for predicting molecular potential energies and forces, which are critical for molecular dynamics simulations. It implements several equivariant neural network architectures including TensorNet, Equivariant Transformers, and Graph Neural Networks, all exposed as PyTorch modules. The trained potentials integrate with GPU-accelerated molecular dynamics codes like ACEMD, OpenMM, and TorchMD for running simulations.
Frequently asked
- What is torchmd/torchmd-net?
- Neural network potential models (TensorNet, Transformers, GNN) for molecular dynamics simulation implemented in PyTorch.
- Is torchmd-net open source?
- Yes — torchmd/torchmd-net is open source, released under the MIT license.
- What language is torchmd-net written in?
- torchmd/torchmd-net is primarily written in Python.
- How popular is torchmd-net?
- torchmd/torchmd-net has 478 stars on GitHub.
- Where can I find torchmd-net?
- torchmd/torchmd-net is on GitHub at https://github.com/torchmd/torchmd-net.