TensorFlow入门基础知识（七）tf.train.exponential_decay的用法

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

Applies exponential decay to the learning rate.

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 a 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 *
                        decay_rate ^ (global_step / decay_steps)

If the argument staircase is True, then global_step /decay_steps is an integer division and the decayed learning rate follows a staircase function.

Example: decay every 100000 steps with a base of 0.96:

...
global_step = tf.Variable(0, trainable=False)
starter_learning_rate = 0.1
learning_rate = tf.exponential_decay(starter_learning_rate, global_step,
                                     100000, 0.96, staircase=True)
optimizer = tf.GradientDescent(learning_rate)
# Passing global_step to minimize() will increment it at each step.
optimizer.minimize(...my loss..., global_step=global_step)

Args:

learning_rate: A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
global_step: A scalar int32 or int64 Tensor or a Python number. Global step to use for the decay computation. Must not be negative.
decay_steps: A scalar int32 or int64 Tensor or a Python number. Must be positive. See the decay computation above.
decay_rate: A scalar float32 or float64 Tensor or a Python number. The decay rate.
staircase: Boolean. It True decay the learning rate at discrete intervals.
name: string. Optional name of the operation. Defaults to 'ExponentialDecay'

Returns:

A scalar Tensor of the same type as learning_rate. The decayed learning rate.

Moving Averages

Some training algorithms, such as GradientDescent and Momentum often benefit from maintaining a moving average of variables during optimization. Using the moving averages for evaluations often improve results significantly.

将指数衰减应用于学习速率。当训练一个模型时，通常建议在训练过程中降低学习速率。该函数将指数衰减函数应用于给定的初始学习速率。它需要一个global_step值来计算衰减的学习速率。你可以通过每个训练步骤中增加的一个TensorFlow变量。函数返回衰减的学习速率。它计算如下：

decayed_learning_rate = learning_rate *
                        decay_rate ^ (global_step / decay_steps)

如果参数staircase 是 True，那么global_step /decay_steps是一个整数除法，而衰减的学习速率遵循一个阶梯函数。

以0.96为基数的每10万步的衰变:

...
global_step = tf.Variable(0, trainable=False)
starter_learning_rate = 0.1
learning_rate = tf.exponential_decay(starter_learning_rate, global_step,
                                     100000, 0.96, staircase=True)
optimizer = tf.GradientDescent(learning_rate)
# Passing global_step to minimize() will increment it at each step.
optimizer.minimize(...my loss..., global_step=global_step)

参数:

learning_rate:最初的学习速率。一个float32或float64张量或一个Python类型数字。
global_step:用于衰变计算的全局步数，不能是负数，int32,或者int64，或者一个Python类型数字。
decay_steps:int32或者int64的Tensor或者一个Python类型数字，参见上面的衰变计算。
decay_rate: nt32或者int64的Tensor或者一个Python类型数字，衰减速率
staircase: Boolean型.它是true时，在离散时间间隔内衰减学习速率。
name: string型.可选项，默认值为 'ExponentialDecay'

返回值：

返回值类型与learn_rate返回值类型相同，返回衰减学习速率