Is There any way to keep the composition of a crystal same , and just predict the structure ?

jiaor17 / DiffCSP

[NeurIPS 2023] The implementation for the paper "Crystal Structure Prediction by Joint Equivariant Diffusion"

MIT License

83 stars 36 forks source link

Closed nitesh-acog closed 9 months ago

nitesh-acog commented 9 months ago

I've trained the model on carbon_24 dataset, but i don't want add noise to the atom_types and get any change in composition while sampling.

nitesh-acog commented 9 months ago

Need to add a feature for Post precessing the pytorch objects.