CosineAnnealingWarmRestarts

class torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(optimizer, T_0, T_mult=1, eta_min=0.0, last_epoch=-1)

Set the learning rate of each parameter group using a cosine annealing schedule.

The $\eta_{max}$ is set to the initial lr, $T_{cur}$ is the number of epochs since the last restart and $T_{i}$ is the number of epochs between two warm restarts in SGDR:

$$\eta_t = \eta_{min} + \frac{1}{2}(\eta_{max} - \eta_{min})\left(1 + \cos\left(\frac{T_{cur}}{T_{i}}\pi\right)\right)$$

When $T_{cur}=T_{i}$, set $\eta_t = \eta_{min}$. When $T_{cur}=0$ after restart, set $\eta_t=\eta_{max}$.

It has been proposed in SGDR: Stochastic Gradient Descent with Warm Restarts.

Parameters

• optimizer (Optimizer) – Wrapped optimizer.

• T_0 (int) – Number of iterations until the first restart.

• T_mult (int, optional) – A factor by which $T_{i}$ increases after a restart. Default: 1.

• eta_min (float, optional) – Minimum learning rate. Default: 0.

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

Example

>>> optimizer = torch.optim.SGD(model.parameters(), lr=0.05)
>>> scheduler = torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(
...     optimizer, T_0=20
... )
>>> for epoch in range(100):
>>>     train(...)
>>>     validate(...)
>>>     scheduler.step()

get_last_lr()

Get the most recent learning rates computed by this scheduler.

Returns

A list of learning rates with entries for each of the optimizer’s param_groups, with the same types as their group["lr"]s.

Return type

list[float | Tensor]

Note

The returned Tensors are copies, and never alias the optimizer’s group["lr"]s.

get_lr()

Compute the next learning rate for each of the optimizer’s param_groups.

Computes learning rates for the optimizer’s param_groups following:

$$\texttt{eta\_min} + \frac{1}{2}(\texttt{base\_lr} - \texttt{eta\_min})\left(1 + \cos\left(\pi \cdot \frac{\texttt{T\_cur}}{\texttt{T\_i}}\right)\right)$$

Where T_cur is the number of epochs since the last restart and T_i is the number of epochs between two restarts. Both T_cur and T_i are updated in step(), and T_i becomes T_mult times larger after each restart.

Returns

A list of learning rates for each of the optimizer’s param_groups with the same types as their current group["lr"]s.

Return type

list[float | Tensor]

Note

If you’re trying to inspect the most recent learning rate, use get_last_lr() instead.

Note

The returned Tensors are copies, and never alias the optimizer’s group["lr"]s.

load_state_dict(state_dict)

Load the scheduler’s state.

Parameters

state_dict (dict) – scheduler state. Should be an object returned from a call to state_dict().

state_dict()

Return the state of the scheduler as a dict.

It contains an entry for every variable in self.__dict__ which is not the optimizer.

Return type

dict[str, Any]

step(epoch=None)

Step could be called after every batch update.

Example

>>> scheduler = CosineAnnealingWarmRestarts(optimizer, T_0, T_mult)
>>> iters = len(dataloader)
>>> for epoch in range(20):
>>>     for i, sample in enumerate(dataloader):
>>>         inputs, labels = sample['inputs'], sample['labels']
>>>         optimizer.zero_grad()
>>>         outputs = net(inputs)
>>>         loss = criterion(outputs, labels)
>>>         loss.backward()
>>>         optimizer.step()
>>>         scheduler.step(epoch + i / iters)

This function can be called in an interleaved way.

Example

>>> scheduler = CosineAnnealingWarmRestarts(optimizer, T_0, T_mult)
>>> for epoch in range(20):
>>>     scheduler.step()
>>> scheduler.step(26)
>>> scheduler.step()  # scheduler.step(27), instead of scheduler(20)