ConstantLR — PyTorch 2.7 documentation (original) (raw)
class torch.optim.lr_scheduler.ConstantLR(optimizer, factor=0.3333333333333333, total_iters=5, last_epoch=-1)[source][source]¶
Multiply the learning rate of each parameter group by a small constant factor.
The multiplication is done until the number of epoch reaches a pre-defined milestone: total_iters. Notice that such multiplication of the small constant factor can happen simultaneously with other changes to the learning rate from outside this scheduler. When last_epoch=-1, sets initial lr as lr.
Parameters
- optimizer (Optimizer) – Wrapped optimizer.
- factor (float) – The number we multiply learning rate until the milestone. Default: 1./3.
- total_iters (int) – The number of steps that the scheduler multiplies the learning rate by the factor. Default: 5.
- last_epoch (int) – The index of the last epoch. Default: -1.
Example
Assuming optimizer uses lr = 0.05 for all groups
lr = 0.025 if epoch == 0
lr = 0.025 if epoch == 1
lr = 0.025 if epoch == 2
lr = 0.025 if epoch == 3
lr = 0.05 if epoch >= 4
scheduler = ConstantLR(optimizer, factor=0.5, total_iters=4) for epoch in range(100): train(...) validate(...) scheduler.step()
Return last computed learning rate by current scheduler.
Return type
Compute the learning rate of each parameter group.
load_state_dict(state_dict)[source]¶
Load the scheduler’s state.
Parameters
state_dict (dict) – scheduler state. Should be an object returned from a call to 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.
Perform a step.