Would it be possible to obtain an already trained .cpkt file with the model used in this project's paper?

Hello, everyone! I have trained one PhysNet model on the solvated_protein_fragments.npz data. Now I want to conduct the MD simulations based on the model through ASE environment. The simulation system I used has 1681 atoms and satisfies PBC conditions. I set the lr_cut 8 Angstrom in the NNCalculator.py.

I found the ASE-MD simulation was running slowly. I submit the task on computation cluster and used one gpu and five cpu cores. However, the simulation of 5000 steps consumes about 6 hours. In the running process, the volatile GPU-Util almost keeps zero, but the memory usage is large.

I think the low speed arises from the ase.neighbor_list process, but I don't know how improve the situation effectively.

Looking forward to your help!

I hope you can help solve the problem. I use anaconda for the creation of a virtual environment and run train.py in spyder with python 3.11. When I run the train.py, there shows up the error. The dataset used by this code is sn2_reactions.npz, which is got from: https://zenodo.org/record/2605341. Other files and parameters are not verified.

THe error report:

File D:\programs\anaconda3\Lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
exec(code, globals, locals)

File d:\programs\qml\copies\physnet-master\physnet-master\train.py:122
Eshift=data_provider.EperA_mean,

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:106 in EperA_mean
self._compute_E_statistics()

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:95 in _compute_E_statistics
tmp = self.get_data(self.idx_train[i])

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:196 in get_data
return self.data[idx]

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataContainer.py:147 in getitem
for k, i in enumerate(idx):

TypeError: 'numpy.int32' object is not iterable

Desktop
OS: [Windows11]
Anaconda version：conda 23.7.3
Python Version: [3.11.4]
Package Version: [tensorflow 2.13.0], [numpy 1.24.3]

Hi,

What is the unit of the MAE value (best_emae) that is printed in train.py line 458? Is it in eV or kcal/mol? If it is kcal/mol, can you please tell me in which part of the code did you do the unit conversion?

Thank you,

I saw that this was ran with qm9, do you know how they were able to get a qm9.npz file that works with the model?