ML ISTART: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 7: Line 7:
*{{TAG|ML_ISTART}}=1: The program reads the training data stored in the {{TAG|ML_AB}} file and restarts the training calculation. Learning is executed.
*{{TAG|ML_ISTART}}=1: The program reads the training data stored in the {{TAG|ML_AB}} file and restarts the training calculation. Learning is executed.
*{{TAG|ML_ISTART}}=2: The program reads the force field parameters stored in the {{TAG|ML_FF}} file and executes calculations using the force field only. No learning is executed.
*{{TAG|ML_ISTART}}=2: The program reads the force field parameters stored in the {{TAG|ML_FF}} file and executes calculations using the force field only. No learning is executed.
*{{TAG»ML_ISTART}}=3: The program reads the training data stored in the {{TAG|ML_AB}} file and selects new local reference configurations from the training data.


== Related Tags and Sections ==
== Related Tags and Sections ==

Revision as of 06:15, 30 August 2021

ML_ISTART = [integer]
Default: ML_ISTART = 0 

Description: This tag decides if and how calculations are continued from existing data in machine learning force field method.


The following cases can be selected:

  • ML_ISTART=0: The training calculations are started from scratch without taking any existing data into considerations. Learning is executed.
  • ML_ISTART=1: The program reads the training data stored in the ML_AB file and restarts the training calculation. Learning is executed.
  • ML_ISTART=2: The program reads the force field parameters stored in the ML_FF file and executes calculations using the force field only. No learning is executed.
  • Template:TAG»ML ISTART=3: The program reads the training data stored in the ML_AB file and selects new local reference configurations from the training data.

Related Tags and Sections

ML_LMLFF, ML_W1, ML_WTOTEN, ML_WTIFOR, ML_WTSIF

Examples that use this tag