DEEPMD
References: Wang2018, Zeng2023
This section specifies the input parameters for Deep Potential type. Mainly intended for things like neural network to DFT to achieve correlated-wavefunction-like accuracy. Requires linking with DeePMD-kit library from https://docs.deepmodeling.com/projects/deepmd/en/master . [Edit on GitHub]
Keywords
Keyword descriptions
- ATOMS: string
Usage: ATOMS {KIND 1} {KIND 2} .. {KIND N}
Mentions: ⭐DeePMD-kit
Defines the atomic kinds involved in the Deep Potential. Provide a list of each element, making sure that the mapping from the ATOMS list to DeePMD atom types is correct. [Edit on GitHub]
- ATOMS_DEEPMD_TYPE: integer
Usage: ATOMS_DEEPMD_TYPE {TYPE INTEGER 1} {TYPE INTEGER 2} .. {TYPE INTEGER N}
Mentions: ⭐DeePMD-kit
Specifies the atomic TYPE for the DeePMD-kit potential. Provide a list of index, making sure that the mapping from the ATOMS list to DeePMD atom types is correct. [Edit on GitHub]
- POT_FILE_NAME: string = graph.pb
Aliases: PARMFILE
Usage: POT_FILE_NAME {FILENAME}
Specifies the filename that contains the DeePMD-kit potential. [Edit on GitHub]