Missed TensorFlow World? Check out the recap. Learn more

tf.contrib.distribute.StandardSingleLossStep

View source on GitHub

Class StandardSingleLossStep

A step function that implements a training step for a feed forward network.

Inherits From: StandardInputStep

An instance of this class is intended to be used as a callable:

...
step = step_fn.StandardSingleLossStep(
    dataset, loss_fn, optimizer, distribution)

# Run a single training step on a given DistributionStrategy:
step(distribution)
...

Args:

  • dataset_fn: a function that returns a tf.data Dataset that produces the input for the model.
  • loss_fn: a function that takes a context and inputs as arguments. It returns the loss for those inputs. context is an instance of values.MultiStepContext that will be passed when loss_fn is run. context can be used to specify the outputs to be returned from loss_fn, among other things.
  • optimizer: an optimizer that implements an update rule.
  • distribution: a DistributionStrategy object.

__init__

View source

__init__(
    dataset_fn,
    loss_fn,
    optimizer,
    distribution,
    iterations_per_step=1
)

Properties

distribution

Methods

__call__

View source

__call__()

initialize

View source

initialize()