deepmd.pt.model.descriptor.dpa2

Module Contents

Classes

DescrptDPA2

Base class for all neural network modules.

class deepmd.pt.model.descriptor.dpa2.DescrptDPA2(ntypes: int, repinit_rcut: float, repinit_rcut_smth: float, repinit_nsel: int, repformer_rcut: float, repformer_rcut_smth: float, repformer_nsel: int, tebd_dim: int = 8, concat_output_tebd: bool = True, repinit_neuron: List[int] = [25, 50, 100], repinit_axis_neuron: int = 16, repinit_set_davg_zero: bool = True, repinit_activation='tanh', repformer_nlayers: int = 3, repformer_g1_dim: int = 128, repformer_g2_dim: int = 16, repformer_axis_dim: int = 4, repformer_do_bn_mode: str = 'no', repformer_bn_momentum: float = 0.1, repformer_update_g1_has_conv: bool = True, repformer_update_g1_has_drrd: bool = True, repformer_update_g1_has_grrg: bool = True, repformer_update_g1_has_attn: bool = True, repformer_update_g2_has_g1g1: bool = True, repformer_update_g2_has_attn: bool = True, repformer_update_h2: bool = False, repformer_attn1_hidden: int = 64, repformer_attn1_nhead: int = 4, repformer_attn2_hidden: int = 16, repformer_attn2_nhead: int = 4, repformer_attn2_has_gate: bool = False, repformer_activation: str = 'tanh', repformer_update_style: str = 'res_avg', repformer_set_davg_zero: bool = True, repformer_add_type_ebd_to_seq: bool = False, env_protection: float = 0.0, trainable: bool = True, exclude_types: List[Tuple[int, int]] = [], type: str | None = None, rcut: float | None = None, rcut_smth: float | None = None, sel: int | None = None)

Bases: torch.nn.Module, deepmd.pt.model.descriptor.base_descriptor.BaseDescriptor

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

property dim_out

property dim_emb

Returns the embedding dimension g2.

get_rcut() → float

Returns the cut-off radius.

get_nsel() → int

Returns the number of selected atoms in the cut-off radius.

get_sel() → List[int]

Returns the number of selected atoms for each type.

get_ntypes() → int

Returns the number of element types.

get_dim_out() → int

Returns the output dimension of this descriptor.

get_dim_emb() → int

Returns the embedding dimension of this descriptor.

mixed_types() → bool

If true, the discriptor 1. assumes total number of atoms aligned across frames; 2. requires a neighbor list that does not distinguish different atomic types.

If false, the discriptor 1. assumes total number of atoms of each atom type aligned across frames; 2. requires a neighbor list that distinguishes different atomic types.

share_params(base_class, shared_level, resume=False)

Share the parameters of self to the base_class with shared_level during multitask training. If not start from checkpoint (resume is False), some seperated parameters (e.g. mean and stddev) will be re-calculated across different classes.

compute_input_stats(merged: Callable[[], List[dict]] | List[dict], path: deepmd.utils.path.DPPath | None = None)

Compute the input statistics (e.g. mean and stddev) for the descriptors from packed data.

Parameters:

mergedUnion[Callable[[], List[dict]], List[dict]]

• List[dict]: A list of data samples from various data systems.

  Each element, merged[i], is a data dictionary containing keys: torch.Tensor originating from the i-th data system.

• Callable[[], List[dict]]: A lazy function that returns data samples in the above format

  only when needed. Since the sampling process can be slow and memory-intensive, the lazy function helps by only sampling once.

pathOptional[DPPath]

The path to the stat file.

abstract serialize() → dict

Serialize the obj to dict.

abstract classmethod deserialize() → DescrptDPA2

Deserialize from a dict.

forward(extended_coord: torch.Tensor, extended_atype: torch.Tensor, nlist: torch.Tensor, mapping: torch.Tensor | None = None, comm_dict: Dict[str, torch.Tensor] | None = None)

Compute the descriptor.

Parameters:

coord_ext

The extended coordinates of atoms. shape: nf x (nallx3)

atype_ext

The extended aotm types. shape: nf x nall

nlist

The neighbor list. shape: nf x nloc x nnei

mapping

The index mapping, mapps extended region index to local region.

comm_dict

The data needed for communication for parallel inference.

Returns:

descriptor

The descriptor. shape: nf x nloc x (ng x axis_neuron)

gr

The rotationally equivariant and permutationally invariant single particle representation. shape: nf x nloc x ng x 3

g2

The rotationally invariant pair-partical representation. shape: nf x nloc x nnei x ng

h2

The rotationally equivariant pair-partical representation. shape: nf x nloc x nnei x 3

sw

The smooth switch function. shape: nf x nloc x nnei

classmethod update_sel(global_jdata: dict, local_jdata: dict)

Update the selection and perform neighbor statistics.

Parameters:

global_jdatadict

The global data, containing the training section

local_jdatadict

The local data refer to the current class