deepmd.tf.utils.neighbor_stat

deepmd.tf.utils.neighbor_stat#

Attributes#

log

Classes#

`NeighborStatOP`	Class for getting neighbor statistics data information.
`NeighborStat`	Class for getting training data information.

Module Contents#

deepmd.tf.utils.neighbor_stat.log[source]#

class deepmd.tf.utils.neighbor_stat.NeighborStatOP(ntypes: int, rcut: float, mixed_types: bool)[source]#

Class for getting neighbor statistics data information.

Parameters:

ntypes: The num of atom types
rcut: The cut-off radius
mixed_typesbool, optional: If True, treat neighbors of all types as a single type.

rcut[source]#

ntypes[source]#

mixed_types[source]#

build(coord: deepmd.tf.env.tf.Tensor, atype: deepmd.tf.env.tf.Tensor, cell: deepmd.tf.env.tf.Tensor, pbc: deepmd.tf.env.tf.Tensor) → tuple[deepmd.tf.env.tf.Tensor, deepmd.tf.env.tf.Tensor][source]#

Calculate the nearest neighbor distance between atoms, maximum nbor size of atoms and the output data range of the environment matrix.

Parameters:

coord: The coordinates of atoms.
atype: The atom types.
cell: The cell.

Returns:

tf.Tensor: The minimal squared distance between two atoms, in the shape of (nframes,)
tf.Tensor: The maximal number of neighbors

class deepmd.tf.utils.neighbor_stat.NeighborStat(ntypes: int, rcut: float, mixed_type: bool = False)[source]#

Bases: deepmd.utils.neighbor_stat.NeighborStat

Class for getting training data information.

It loads data from DeepmdData object, and measures the data info, including neareest nbor distance between atoms, max nbor size of atoms and the output data range of the environment matrix.

Parameters:

ntypes: The num of atom types
rcut: The cut-off radius
mixed_typebool, optional, default=False: Treat all types as a single type.

auto_batch_size[source]#

neighbor_stat[source]#

place_holders[source]#

sub_sess[source]#

build() → tuple[deepmd.tf.env.tf.Tensor, deepmd.tf.env.tf.Tensor][source]#

Build the graph.

Returns:

tf.Tensor: The minimal squared distance between two atoms, in the shape of (nframes,)
tf.Tensor: The maximal number of neighbors

iterator(data: deepmd.tf.utils.data_system.DeepmdDataSystem) → collections.abc.Iterator[tuple[numpy.ndarray, float, str]][source]#

Produce data.

Parameters:

data: The data system

Yields:

np.ndarray: The maximal number of neighbors
float: The squared minimal distance between two atoms
str: The directory of the data system

_execute(coord: numpy.ndarray, atype: numpy.ndarray, box: numpy.ndarray | None, pbc: bool) → tuple[numpy.ndarray, numpy.ndarray][source]#

Execute the operation.

Parameters:

coord: The coordinates of atoms.
atype: The atom types.
box: The box.
pbc: Whether the box is periodic.