src.model.deeplearn.optimizer.centralized_sgd

Classes

CentralizedSGD([learning_rate, momentum, ...])

Stochastic gradient descent optimizer with centralized gradients.

class src.model.deeplearn.optimizer.centralized_sgd.CentralizedSGD(learning_rate=0.01, momentum=0.0, nesterov=False, weight_decay=None, clipnorm=None, clipvalue=None, global_clipnorm=None, use_ema=False, ema_momentum=0.99, ema_overwrite_frequency=None, loss_scale_factor=None, gradient_accumulation_steps=None, name='SGD', **kwargs)

Stochastic gradient descent optimizer with centralized gradients. The optimizer behaves exactly like keras.optimizers.SGD but its gradients are centered.

update_step(gradient, variable, learning_rate)

Modify the gradients of the backbone optimizer by centering them before applying them to fit the model’s parameters.

See CentralizedAdam.center_gradients().

Returns:

Nothing at all, but the parameters are updated with the centered gradients instead of the original ones.