LinearLR#

classtorch.optim.lr_scheduler.LinearLR(optimizer,start_factor=0.3333333333333333,end_factor=1.0,total_iters=5,last_epoch=-1)[source]#

Decays the learning rate of each parameter group by linearly changing small multiplicative factor.

The multiplication is done until the number of epoch reaches a pre-defined milestone: total_iters.Notice that such decay can happen simultaneously with other changes to the learning ratefrom outside this scheduler. When last_epoch=-1, sets initial lr as lr.

Parameters

• optimizer (Optimizer) – Wrapped optimizer.

• start_factor (float) – The number we multiply learning rate in the first epoch.The multiplication factor changes towards end_factor in the following epochs.Default: 1./3.

• end_factor (float) – The number we multiply learning rate at the end of linear changingprocess. Default: 1.0.

• total_iters (int) – The number of iterations that multiplicative factor reaches to 1.Default: 5.

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

Example

>>># Assuming optimizer uses lr = 0.05 for all groups>>># lr = 0.003687  if epoch == 0>>># lr = 0.004875  if epoch == 1>>># lr = 0.006062  if epoch == 2>>># lr = 0.00725   if epoch == 3>>># ...>>># lr = 0.05      if epoch >= 40>>>scheduler=LinearLR(optimizer,start_factor=0.05,total_iters=40)>>>forepochinrange(100):>>>train(...)>>>validate(...)>>>scheduler.step()

get_last_lr()[source]#

Return last computed learning rate by current scheduler.

Return type

list[float]

get_lr()[source]#

Compute the learning rate.

Return type

list[float]

load_state_dict(state_dict)[source]#

Load the scheduler’s state.

Parameters

state_dict (dict) – scheduler state. Should be an object returnedfrom a call tostate_dict().

state_dict()[source]#

Return the state of the scheduler as adict.

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

Return type

dict[str,Any]

step(epoch=None)[source]#

Perform a step.