Yu Xie
Hi @wontleave , I checked your files and tried running it with lammps, if you check your std out/err file, you will find the error message from lammps: ``` 71...
Hi @wontleave I notice that your .mgp potential file has the coefficients for C, H, O, while your lammps simulation is just for small molecules with C and H. So...
Hi @wontleave It will make more sense to have the same system for training and testing data. So I would suggest that you either simulate with water+toluene to see if...
Hi @wontleave > I wonder what is the correct procedure to add training data to an existing GP. You can either run an on-the-fly training, for which you can refer...
Hi @fgimbert, thanks for reporting this issue. Just a few questions (since recently there're some issues #269 #273 related to the ASE OTF training) - Did you restart your training...
> Hi ! > I was able to do more tests and I found that with use_mapping = False, the temperature was not exploding anymore. For now I will use...
Hi @xig126, for 2-body mapping, you can set a large number of grid (128 or larger), it is ok because 2-body mapping is always very cheap to build. For 3-body...
@aaronchen0316 , thanks for reporting this, and sorry for the late response because I'm recently traveling. If you have an idea how to resolve it (e.g. adding the variables in...
Hi @xig126, for the issue that std. dev are all zeros, I see from your script that you set ``` mgp_model = MappedGaussianProcess(grid_params, unique_species = [13], n_cpus = 1, var_map=None)...
Close stale issue