tf.train.natural_exp_decay

View source on GitHub

Applies natural exponential decay to the initial learning rate.

tf.train.natural_exp_decay(
    learning_rate, global_step, decay_steps, decay_rate, staircase=False, name=None
)

When training a model, it is often recommended to lower the learning rate as the training progresses. This function applies an exponential decay function to a provided initial learning rate. It requires an global_step value to compute the decayed learning rate. You can just pass a TensorFlow variable that you increment at each training step.

The function returns the decayed learning rate. It is computed as:

decayed_learning_rate = learning_rate * exp(-decay_rate * global_step /
decay_step)

or, if staircase is True, as:

decayed_learning_rate = learning_rate * exp(-decay_rate * floor(global_step /
decay_step))

Example: decay exponentially with a base of 0.96:

...
global_step = tf.Variable(0, trainable=False)
learning_rate = 0.1
decay_steps = 5
k = 0.5
learning_rate = tf.compat.v1.train.natural_exp_decay(learning_rate,
global_step,
                                           decay_steps, k)

# Passing global_step to minimize() will increment it at each step.
learning_step = (
    tf.compat.v1.train.GradientDescentOptimizer(learning_rate)
    .minimize(...my loss..., global_step=global_step)
)

Eager Compatibility

When eager execution is enabled, this function returns a function which in turn returns the decayed learning rate Tensor. This can be useful for changing the learning rate value across different invocations of optimizer functions.