LinearMomentum¶
- class mmengine.optim.LinearMomentum(optimizer, *args, **kwargs)[source]¶
Decays the momentum of each parameter group by linearly changing small multiplicative factor until the number of epoch reaches a pre-defined milestone:
end
.Notice that such decay can happen simultaneously with other changes to the momentum from outside this scheduler.
- Parameters:
optimizer (Optimizer or OptimWrapper) – optimizer or Wrapped optimizer.
start_factor (float) – The number we multiply momentum in the first epoch. The multiplication factor changes towards end_factor in the following epochs. Defaults to 1./3.
end_factor (float) – The number we multiply momentum at the end of linear changing process. Defaults to 1.0.
begin (int) – Step at which to start updating the momentum. Defaults to 0.
end (int) – Step at which to stop updating the momentum. Defaults to INF.
last_step (int) – The index of last step. Used for resume without state dict. Defaults to -1.
by_epoch (bool) – Whether the scheduled momentum is updated by epochs. Defaults to True.
verbose (bool) – Whether to print the momentum for each update. Defaults to False.