deepmd.tf.nvnmd.utils.weight

Module Contents

Functions

get_weight(weights, key)	Get weight value according to key.
get_normalize(weights)	Get normalize parameter (avg and std) of \(s_{ji}\).
get_type_embedding_weight(weights, layer_l)	Get weight and bias of type_embedding network.
get_filter_weight(weights, spe_j, layer_l)	Get weight and bias of embedding network.
get_filter_type_weight(weights, layer_l)	Get weight and bias of two_side_type_embedding network.
get_fitnet_weight(weights, spe_i, layer_l[, nlayer])	Get weight and bias of fitting network.
get_type_weight(weights, layer_l)	Get weight and bias of fitting network.
get_constant_initializer(weights, name)	Get initial value by name and create a initializer.

Attributes

log

deepmd.tf.nvnmd.utils.weight.log

deepmd.tf.nvnmd.utils.weight.get_weight(weights, key)

Get weight value according to key.

deepmd.tf.nvnmd.utils.weight.get_normalize(weights: dict)

Get normalize parameter (avg and std) of \(s_{ji}\).

deepmd.tf.nvnmd.utils.weight.get_type_embedding_weight(weights: dict, layer_l: int)

Get weight and bias of type_embedding network.

Parameters:

weightsdict

weights

layer_l

layer order in embedding network 1~nlayer

deepmd.tf.nvnmd.utils.weight.get_filter_weight(weights: int, spe_j: int, layer_l: int)

Get weight and bias of embedding network.

Parameters:

weightsdict

weights

spe_jint

special order of neighbor atom j 0~ntype-1

layer_l

layer order in embedding network 1~nlayer

deepmd.tf.nvnmd.utils.weight.get_filter_type_weight(weights: dict, layer_l: int)

Get weight and bias of two_side_type_embedding network.

Parameters:

weightsdict

weights

layer_l

layer order in embedding network 1~nlayer

deepmd.tf.nvnmd.utils.weight.get_fitnet_weight(weights: dict, spe_i: int, layer_l: int, nlayer: int = 10)

Get weight and bias of fitting network.

Parameters:

weightsdict

weights

spe_iint

special order of central atom i 0~ntype-1

layer_lint

layer order in embedding network 0~nlayer-1

nlayerint

number of layers

deepmd.tf.nvnmd.utils.weight.get_type_weight(weights: dict, layer_l: int)

Get weight and bias of fitting network.

Parameters:

weightsdict

weights

layer_lint

layer order in embedding network 0~nlayer-1

deepmd.tf.nvnmd.utils.weight.get_constant_initializer(weights, name)

Get initial value by name and create a initializer.