Duo

Results 26 comments of Duo

feat(finetune): add warnings for descriptor config changes during fine-tuning with proper default handling

@copilot can you wrap up and simplify all the modifications in this PR? It seems that there are lots of duplicated lines.

PyTorch Backend: Missing autograd wrapper for se_t descriptor's second-order derivatives

@OutisLi The virial/stress only needs first-order derivative as same as force, while the second-order derivative calculations are for training. @njzjz I'm also confusing that it seems that even for se_a,...

[BUG] _DeePMD-kit C API Error: DeePMD-kit Error: DeePMD-kit PyTorch backend error: The following operation failed in the TorchScript interpreter.

Hi @myyelishu , could you: 1. Also provide the error log of se_a model of pytorch during LAMMPS MD. 2. Try the newst version of DeePMD-kit (version 3.1.1): https://github.com/deepmodeling/deepmd-kit/releases/tag/v3.1.1 which...

[BUG] Changing `nlayer` lead no error report while fine-tuning

It seems that now only **the missing keys** in the checkpoint will through an error, but not for the **extra keys** (it is the case if you set a smaller...

fix(pt): make int `rcut` safe after jit op

I've tried adding type annotation `Union[int, float]` and float convertion in `prod_env_mat` or `build_multiple_neighbor_list` etc, but found that it's much less robust for developers to contain such convertion in other...

[BUG] DPA2 Lammps on nopbc systems causes torchscript error

It seems not easy to resolve so far. 1. Lammps using pytorch dpa1 and se_a works for nopbc systems. 2. dp test always work for nopbc systems. 3. Lammps using...