ml.optimizers.sgd

Defines a simple SGD optimizer.

class ml.optimizers.sgd.SGDOptimizerConfig(name: str = '???', lr: float = 0.001, momentum: float = 0.0, dampening: float = 0.0, nesterov: bool = False, weight_decay: float = 1e-05, default_decay: bool = True)

Bases: BaseOptimizerConfig

lr: float = 0.001

momentum: float = 0.0

dampening: float = 0.0

nesterov: bool = False

weight_decay: float = 1e-05

default_decay: bool = True

class ml.optimizers.sgd.SGDOptimizer(config: BaseConfigT)

Bases: BaseOptimizer[SGDOptimizerConfig, SGD]

get(model: Module) → SGD

Given a base module, returns an optimizer.

Parameters:

model – The model to get an optimizer for

Returns:

The constructed optimizer