ExponentialMomentum¶
- class mmengine.optim.ExponentialMomentum(optimizer, *args, **kwargs)[source]¶
Decays the momentum of each parameter group by gamma every epoch.
- Parameters:
optimizer (Optimizer or OptimWrapper) – optimizer or Wrapped optimizer.
gamma (float) – Multiplicative factor of momentum value decay.
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.