mindspore.experimental.optim.lr_scheduler.CosineAnnealingLR

class mindspore.experimental.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max, eta_min=0.0, last_epoch=- 1)

Set the learning rate of each parameter group using a cosine annealing lr schedule. Where ${\eta }_{max}$ is set to the initial lr, ${\eta }_{min}$ is the minimum value for learning rate, ${\eta }_t$ is the current learning rate, $T_{max}$ is iteration number of cosine function, and $T_{cur}$ is the number of epochs since the last restart in SGDR.

$$\begin{array}{r}\begin{array}{rlr}{\eta }_t& ={\eta }_{min}+\frac{1}{2}({\eta }_{max}-{\eta }_{min})(1+\cos \left(\frac{T_{cur}}{T_{max}}\pi \right)),& T_{cur}\ne (2k+1)T_{max};\\ {\eta }_{t+1}& ={\eta }_t+\frac{1}{2}({\eta }_{max}-{\eta }_{min})(1-\cos \left(\frac{1}{T_{max}}\pi \right)),& T_{cur}=(2k+1)T_{max}.\end{array}\end{array}$$

For more details, please refer to: SGDR: Stochastic Gradient Descent with Warm Restarts .

Warning

This is an experimental lr scheduler module that is subject to change. This module must be used with optimizers in Experimental Optimizer .

Parameters

• optimizer (mindspore.experimental.optim.Optimizer) – Wrapped optimizer.

• T_max (int) – Maximum number of iterations.

• eta_min (float, optional) – Minimum learning rate. Default: 0.0.

• last_epoch (int, optional) – The index of the last epoch. Default: -1.

Supported Platforms:

Ascend GPU CPU

Examples

>>> from mindspore.experimental import optim
>>> from mindspore import nn
>>> net = nn.Dense(3, 2)
>>> optimizer = optim.SGD(net.trainable_params(), lr=0.1, momentum=0.9)
>>> scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=2)
>>>
>>> for i in range(6):
...     scheduler.step()
...     current_lr = scheduler.get_last_lr()
...     print(current_lr)
[Tensor(shape=[], dtype=Float32, value= 0.05)]
[Tensor(shape=[], dtype=Float32, value= 0)]
[Tensor(shape=[], dtype=Float32, value= 0.05)]
[Tensor(shape=[], dtype=Float32, value= 0.1)]
[Tensor(shape=[], dtype=Float32, value= 0.05)]
[Tensor(shape=[], dtype=Float32, value= 0)]