class

ExponentialLR

extends_LRScheduler

ExponentialLR(optimizer: Optimizer, gamma: float, last_epoch: int = -1, verbose: bool = False)

source edit

Decay the learning rate by a constant factor every epoch.

The learning rate is multiplied by gamma at every epoch, producing an exponential decay over time:

\eta_t = \eta_0 \cdot \gamma^{t}

Parameters

optimizerOptimizer

Wrapped optimizer.

gammafloat

Multiplicative factor applied each epoch. Values in (0, 1) produce decay; values greater than 1 produce growth (rarely useful).

last_epochint= -1

The index of the last epoch (default: -1).

verbosebool= False

Print the updated LR after each step if True (default: False).

Attributes

gammafloat

Multiplicative factor applied each epoch.

Notes

ExponentialLR applies the decay at every epoch without any plateau detection. For a coarser schedule that decays only at certain milestones, prefer StepLR or MultiStepLR.

Examples

>>> import lucid.nn as nn
>>> model = nn.Linear(4, 2)
>>> import lucid.optim as optim
>>> optimizer = optim.SGD(model.parameters(), lr=0.1)
>>> scheduler = optim.ExponentialLR(optimizer, gamma=0.95)
>>> import lucid.nn as nn
>>> import lucid.optim as optim
>>> model = nn.Linear(4, 2)
>>> optimizer = optim.SGD(model.parameters(), lr=0.1)
>>> for epoch in range(100):
...     optimizer.step()

Used by 1

lucid.optim

Constructors

dunder

init

→None

__init__(optimizer: Optimizer, gamma: float, last_epoch: int = -1, verbose: bool = False)

source edit

Initialise the ExponentialLR. See the class docstring for parameter semantics.

Instance methods

get_lr

→list[float]

get_lr()

source edit

Compute the learning rate for each parameter group at the current step.

Returns

list[float]

One learning rate per param group, derived from the schedule formula documented in the class docstring.

>>> import lucid.nn as nn >>> model = nn.Linear(4, 2) >>> import lucid.optim as optim >>> optimizer = optim.SGD(model.parameters(), lr=0.1) >>> scheduler = optim.ExponentialLR(optimizer, gamma=0.95) >>> import lucid.nn as nn >>> import lucid.optim as optim >>> model = nn.Linear(4, 2) >>> optimizer = optim.SGD(model.parameters(), lr=0.1) >>> for epoch in range(100): ... optimizer.step()