Zheyong Fan
Zheyong Fan
**Summary** Some box shapes in the training (or testing) set are not supported. **Deepmd-kit Version, Python Version, Tensorflow Version, GCC Version and Cuda Version.** The issue should be applicable to...
This is important for fluids and might also have small effects in some solid structures.
Calculating the lattice thermal conductivity based on the Boltzmann transport equation (BTE) and lattice dynamics (harmonic and anharmonic).
Implement one or more PIMD methods, such as ring polymer MD. This should be done at some point.
Penghua has suggested to save one `nep.txt` every 1e5 generations. Then if one trains for 5e5 generations, there will be 5 candidate NEP models that can be used for comparison....
* use case 1: on-the-fly calculation of model uncertainty * use case 2: multiple different PESs are needed for e.g., ground and excited states
The user might use unwrapped trajectory to create a training/testing data set and that requires a proper wrapping after reading in the structures.