RMSprop¶

class dragon.vm.tensorflow.keras.optimizers.RMSprop(
learning_rate=0.001,
rho=0.9,
momentum=0.0,
epsilon=1e-07,
name=None,
**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__(
learning_rate=0.001,
rho=0.9,
momentum=0.0,
epsilon=1e-07,
name=None,
**kwargs
)[source]¶

Create a RMSprop optimizer.

Parameters:

learning_rate (float, optional, default=0.001) – The initial value to \(\text{lr}\).
rho (float, optional, default=0.9) – The initial value to \(\alpha\).
momentum (float, optional, default=0) – The initial value to \(\text{momentum}\).
epsilon (float, optional, default=1e-7) – The initial value to \(\epsilon\).
name (str, optional) – The optional optimizer name.

Properties¶

iterations¶

Optimizer.iterations

Return the number of steps has run.

Returns:: int – The iterations.

Methods¶

apply_gradients¶

Optimizer.apply_gradients(grads_and_vars)[source]

Apply the gradients to update variables.