Author Topic: AIMD trajectory to MTP training data  (Read 37 times)

0 Members and 1 Guest are viewing this topic.

Offline fangbiaolee

  • New ATK user
  • *
  • Posts: 2
  • Country: cn
  • Reputation: 0
    • View Profile
AIMD trajectory to MTP training data
« on: June 22, 2022, 04:28 »
Dear ATK-Staff/developer:
when I loaded the AIMD trajectory object which was precalculated:

# Load another Trajectory object with precalculated data.
trajectory_training_data_input = nlread('KPF6_MD_trajectory_300K_0.1GPa.hdf5', Trajectory)[0]
training_sets.append(
   TrainingSet(trajectory_training_data_input,
                       # sample_size=100,
                        calculator=calculator,
                        recalculate_training_data=False)

I encountered the following problem:

Traceback (most recent call last):
  File "test3.py", line 58, in <module>
trajectory_training_data_input=nlread('KPF6_MD_trajectory_300K_0.1GPa.hdf5', Trajectory)[0]
IndexError: list index out of range
application called MPI_Abort(MPI_COMM_WORLD, 1) - process 31

The  measurements of MD_trajectory are shown as follow: kinetic_energy, potential_energy, volume, temperature, pressure and stress.
And that are differs from the “energy”, “force” and “stress”required for the training set. Moreover,  there is no option for “force” in the measurements  in AIMD simulation.

So how do I solve this problem so that I can make use of the AIMD data that has been calculated before.



« Last Edit: June 22, 2022, 04:31 by fangbiaolee »