Google I / O가 5 월 18 ~ 20 일에 돌아옵니다! 공간을 예약하고 일정을 짜세요 지금 등록하세요

tf.compat.v1.train.linear_cosine_decay

Applies linear cosine decay to the learning rate.

Note that linear cosine decay is more aggressive than cosine decay and larger initial learning rates can typically be used.

When training a model, it is often recommended to lower the learning rate as the training progresses. This function applies a linear 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)
linear_decay = (decay_steps - global_step) / decay_steps)
cosine_decay = 0.5 * (
    1 + cos(pi * 2 * num_periods * global_step / decay_steps))
decayed = (alpha + linear_decay) * cosine_decay + beta
decayed_learning_rate = learning_rate * decayed

Example usage:

decay_steps = 1000
lr_decayed = linear_cosine_decay(learning_rate, global_step, decay_steps)

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.
decay_steps A scalar int32 or int64 Tensor or a Python number. Number of steps to decay over.
num_periods Number of periods in the cosine part of the decay. See computation above.
alpha See computation above.
beta See computation above.
name String. Optional name of the operation. Defaults to 'LinearCosineDecay'.

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

ValueError if global_step is not supplied.

References:

Neural Optimizer Search with Reinforcement Learning: Bello et al., 2017 (pdf) Stochastic Gradient Descent with Warm Restarts: Loshchilov et al., 2017 (pdf)

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.