torchmd-net
torchmd-net copied to clipboard
torchmd
Neural network potentials
This is a proof-of-concept. DO NOT MERGER! - [x] Python wrapper - [x] CPU - [x] Forward pass - [x] CUDA - [x] Forward pass - [x] Backward pass -...
This is just a proof of concept. DO NOT MERGE! - [x] Implement `DistanceBruteForce` - [x] Integrate into `TorchMD_GN` - [x] Make compatible with CUDA Graphs - [x] Tests -...
I've started looking into how to improve the speed of the equivariant transformer. I'm opening this issue as a place to report my progress. I'm mainly interested in the speed...
I've been experimenting with training protocols to see what gives the best results. So far, the best I've found is to start with a large learning rate that pushes the...
Implement the support of atom-wise (e.g. atomic reference energies) and molecule-wise (e.g. electrostatic term) priors. - [x] Refactor the priors - [x] Implement pre-reduce and post-reduce methods
DO NOT MERGE! - [x] Enable to train on the partial charges
This is the first piece of #26. It isn't fully tested yet, but I think it's ready for a first round of comments. I created a mechanism for passing arguments...
I want to implement some physics based priors. An example would be a Coulomb interaction based on pre-computed partial charges that are stored in the dataset. `BasePrior.forward()` is supposed to...
I have a model created with TorchMD-Net. I want to use it for running a simulation in OpenMM. That involves compiling to TorchScript, saving to a file, and loading it...