Python v0.3.0a0+494774d

RMSprop

class dragon.optimizers.RMSprop(
  lr=0.01,
  momentum=0,
  alpha=0.9,
  eps=1e-08,
  **kwargs
)[source]

The optimizer to apply RMSprop algorithm. [Hinton et.al, 2013].

The RMSprop update is defined as:

\[\text{RMSprop}(g) = \text{lr} * m_{t} \\ \quad \\ \text{where} \quad \begin{cases} v_{t} = \alpha * v_{t-1} + (1 - \alpha) * g^{2} \\ m_{t} = \text{momentum} * m_{t-1} + \frac{g}{\sqrt{v_{t}} + \epsilon} \end{cases} \]

__init__

RMSprop.__init__(
  lr=0.01,
  momentum=0,
  alpha=0.9,
  eps=1e-08,
  **kwargs
)[source]

Create a RMSProp optimizer.

Parameters:
  • lr (float, optional, default=0.01) – The initial value to \(\text{lr}\).
  • momentum (float, optional, default=0) – The initial value to \(\text{momentum}\).
  • alpha (float, optional, default=0.9) – The initial value to \(\alpha\).
  • eps (float, optional, default=1e-8) – The initial value to \(\epsilon\).

Methods

apply_gradients

Optimizer.apply_gradients(grads_and_vars)[source]

Apply the gradients on variables.

Parameters:
  • grads_and_vars (Sequence[Sequence[dragon.Tensor]]) – The sequence of update pair.