espnet2.optimizers.sgd.SGD

source

class espnet2.optimizers.sgd.SGD(params, lr: float = 0.1, momentum: float = 0.0, dampening: float = 0.0, weight_decay: float = 0.0, nesterov: bool = False)

Bases: SGD

Thin inheritance of torch.optim.SGD to bind the required arguments, ‘lr’

Note that the arguments of the optimizer invoked by AbsTask.main() must have default value except for ‘param’.

I can’t understand why only SGD.lr doesn’t have the default value.