deepmd.tf.nvnmd.fit.ener

Module Contents

Functions

one_layer_nvnmd(inputs, outputs_size[, activation_fn, ...])

Build one layer with continuous or quantized value.

Attributes

GLOBAL_TF_FLOAT_PRECISION
nvnmd_cfg

deepmd.tf.nvnmd.fit.ener.GLOBAL_TF_FLOAT_PRECISION

deepmd.tf.nvnmd.fit.ener.nvnmd_cfg

deepmd.tf.nvnmd.fit.ener.one_layer_nvnmd(inputs, outputs_size, activation_fn=tf.nn.tanh, precision=GLOBAL_TF_FLOAT_PRECISION, stddev=1.0, bavg=0.0, name='linear', reuse=None, seed=None, use_timestep=False, trainable=True, useBN=False, uniform_seed=False, initial_variables=None, mixed_prec=None, final_layer=False)

Build one layer with continuous or quantized value. Its weight and bias can be initialed with random or constant value.