|View source on GitHub|
Applies cosine decay to the learning rate.
tf.train.cosine_decay( learning_rate, global_step, decay_steps, alpha=0.0, name=None )
See [Loshchilov & Hutter, ICLR2016], SGDR: Stochastic Gradient Descent with Warm Restarts. https://arxiv.org/abs/1608.03983
When training a model, it is often recommended to lower the learning rate as
the training progresses. This function applies a cosine 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:
global_step = min(global_step, decay_steps) cosine_decay = 0.5 * (1 + cos(pi * global_step / decay_steps)) decayed = (1 - alpha) * cosine_decay + alpha decayed_learning_rate = learning_rate * decayed
decay_steps = 1000 lr_decayed = cosine_decay(learning_rate, global_step, decay_steps)
learning_rate: A scalar
float64Tensor or a Python number. The initial learning rate.
global_step: A scalar
Tensoror a Python number. Global step to use for the decay computation.
decay_steps: A scalar
Tensoror a Python number. Number of steps to decay over.
alpha: A scalar
float64Tensor or a Python number. Minimum learning rate value as a fraction of learning_rate.
name: String. Optional name of the operation. Defaults to 'CosineDecay'.
Tensor of the same type as
learning_rate. The decayed
global_stepis not supplied.
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.