class MXNet::Optimizer::SGD
- MXNet::Optimizer::SGD
- MXNet::Optimizer
- Reference
- Object
Overview
The SGD optimizer with momentum and weight decay.
Updates are calculated by:
rescaled_grad = lr * (rescale_grad * clip(grad, clip_gradient) + wd * weight)
state = momentum * state + rescaled_grad
weight = weight - stateDefined in:
mxnet/optimizer.crConstructors
-
.new(momentum = 0.0, **kwargs)
Creates a new instance.
Instance Method Summary
Instance methods inherited from class MXNet::Optimizer
create_state(index, weight)
create_state,
lr : Float64
lr,
rescale_grad : Float64
rescale_grad,
rescale_grad=(rescale_grad)
rescale_grad=,
set_lr_mult(lr_mult)
set_lr_mult,
set_wd_mult(wd_mult)
set_wd_mult,
update(index, weight, gradient, state)
update,
wd : Float64
wd
Constructor methods inherited from class MXNet::Optimizer
new(rescale_grad = 1.0, clip_gradient = -1.0, lr = 0.01, wd = 0.0)
new
Class methods inherited from class MXNet::Optimizer
create(optimizer, **kwargs)
create
Constructor Detail
def self.new(momentum = 0.0, **kwargs)
#
Creates a new instance.
This optimizer accepts the following parameters in addition to
those accepted by Optimizer.
Parameters
- momentum (
Float, optional) The momentum value.