torch.optim.lr_scheduler.MultiStepLR Class Reference

Inheritance diagram for torch.optim.lr_scheduler.MultiStepLR:

Public Member Functions
def	__init__ (self, optimizer, milestones, gamma=0.1, last_epoch=-1)
def	get_lr (self)
Public Member Functions inherited from torch.optim.lr_scheduler._LRScheduler
def	__init__ (self, optimizer, last_epoch=-1)
def	state_dict (self)
def	load_state_dict (self, state_dict)
def	get_lr (self)
def	step (self, epoch=None)

Public Attributes
	milestones
	gamma
Public Attributes inherited from torch.optim.lr_scheduler._LRScheduler
	optimizer
	base_lrs
	last_epoch

Detailed Description

Decays the learning rate of each parameter group by gamma once the
number of epoch reaches one of the milestones. Notice that such decay can
happen simultaneously with other changes to the learning rate from outside
this scheduler. When last_epoch=-1, sets initial lr as lr.

Args:
    optimizer (Optimizer): Wrapped optimizer.
    milestones (list): List of epoch indices. Must be increasing.
    gamma (float): Multiplicative factor of learning rate decay.
        Default: 0.1.
    last_epoch (int): The index of last epoch. Default: -1.

Example:
    >>> # Assuming optimizer uses lr = 0.05 for all groups
    >>> # lr = 0.05     if epoch < 30
    >>> # lr = 0.005    if 30 <= epoch < 80
    >>> # lr = 0.0005   if epoch >= 80
    >>> scheduler = MultiStepLR(optimizer, milestones=[30,80], gamma=0.1)
    >>> for epoch in range(100):
    >>>     scheduler.step()
    >>>     train(...)
    >>>     validate(...)

Definition at line 164 of file lr_scheduler.py.

---

The documentation for this class was generated from the following file:

• torch/optim/lr_scheduler.py