deepr.optimizers.TensorflowOptimizer

class deepr.optimizers.TensorflowOptimizer(optimizer, learning_rate, loss='loss', grad_norms=None, exclude_vars=None, clip=None, skip_vars=None, skip_steps=None, **kwargs)[source]

Default Tensorflow Optimizers

learning_rate

Learning rate

Type:: float

optimizer

Name of the optimizer. See TensorflowOptimizer.OPTIMIZERS for a description of available Tensorflow optimizers.

Type:: str

kwargs: Optional arguments for the Tensorflow optimizer.

__init__(optimizer, learning_rate, loss='loss', grad_norms=None, exclude_vars=None, clip=None, skip_vars=None, skip_steps=None, **kwargs)[source]

Methods

__init__(optimizer, learning_rate[, loss, ...])

Attributes

OPTIMIZERS