Why not use batch norm?

[AlexanderOnly]

Hello, I was wondering what is the "timestep" here, and why not use batch normalization?

deepmd/utils/network.py

if activation_fn != None and use_timestep :
idt_initializer = tf.random_normal_initializer(
stddev=0.001,
mean=0.1,
seed=seed if (seed is None or uniform_seed) else seed + 2)
if initial_variables is not None:
idt_initializer = tf.constant_initializer(initial_variables[name + '/idt'])
idt = tf.get_variable('idt',
[outputs_size],
precision,
idt_initializer,
trainable = trainable)
variable_summaries(idt, 'idt')
if activation_fn != None:
if useBN:
None
# hidden_bn = self._batch_norm(hidden, name=name+'_normalization', reuse=reuse)
# return activation_fn(hidden_bn)
else:
if use_timestep :
return tf.reshape(activation_fn(hidden), [-1, outputs_size]) * idt
else :
return tf.reshape(activation_fn(hidden), [-1, outputs_size])
else:
if useBN:
None
# return self._batch_norm(hidden, name=name+'_normalization', reuse=reuse)
else:
return hidden