mindspore.nn.inverse_decay_lr

mindspore.nn.inverse_decay_lr(learning_rate, decay_rate, total_step, step_per_epoch, decay_epoch, is_stair=False)

Calculates learning rate base on inverse-time decay function. The learning rate for each step will be stored in a list.

For the i-th step, the formula of computing decayed_learning_rate[i] is:

\[decayed\_learning\_rate[i] = learning\_rate / (1 + decay\_rate * current\_epoch / decay\_epoch)\]

Where \(current\_epoch=floor(\frac{i}{step\_per\_epoch})\).

Parameters

• learning_rate (float) – The initial value of learning rate.

• decay_rate (float) – The decay rate.

• total_step (int) – The total number of steps.

• step_per_epoch (int) – The number of steps in per epoch.

• decay_epoch (int) – Number of epochs to decay over.

• is_stair (bool) – If true, learning rate is decayed once every decay_epoch times. If False, the learning rate decays for every epoch. Default: False .

Returns

list[float]. The size of list is total_step.

Raises

• TypeError – If total_step or step_per_epoch or decay_epoch is not an int.

• TypeError – If is_stair is not a bool.

• TypeError – If learning_rate or decay_rate is not a float.

• ValueError – If learning_rate or decay_rate is less than or equal to 0.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore.nn as nn
>>>
>>> learning_rate = 0.1
>>> decay_rate = 0.5
>>> total_step = 6
>>> step_per_epoch = 1
>>> decay_epoch = 1
>>> lr = nn.inverse_decay_lr(learning_rate, decay_rate, total_step, step_per_epoch, decay_epoch, True)
>>> net = nn.Dense(2, 3)
>>> optim = nn.SGD(net.trainable_params(), learning_rate=lr)