Adam¶

class dragon.vm.tensorflow.keras.optimizers.Adam(
learning_rate=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-07,
name=None,
**kwargs
)[source]¶

The optimizer to apply Adam algorithm. [Kingma & Ba, 2014].

The Adam update is defined as:

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

init¶

Adam.__init__(
learning_rate=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-07,
name=None,
**kwargs
)[source]¶

Create an Adam optimizer.

Parameters:

learning_rate (float, optional, default=0.001) – The initial value to \(\text{lr}\).
beta_1 (float, optional, default=0.9) – The initial value to \(\beta_{1}\).
beta_2 (float, optional, default=0.999) – The initial value to \(\beta_{2}\).
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.