tf.train.MonitoredSession.StepContext

Class StepContext

Aliases:

  • Class tf.train.MonitoredSession.StepContext
  • Class tf.train.SingularMonitoredSession.StepContext

Defined in tensorflow/python/training/monitored_session.py.

Control flow instrument for the step_fn from run_step_fn().

Users of step_fn may perform run() calls without running hooks by accessing the session. A run() call with hooks may be performed using run_with_hooks(). Computation flow can be interrupted using request_stop().

Properties

session

Methods

__init__

__init__(
    session,
    run_with_hooks_fn
)

Initializes the step_context argument for a step_fn invocation.

Args:

  • session: An instance of tf.Session.
  • run_with_hooks_fn: A function for running fetches and hooks.

request_stop

request_stop()

Exit the training loop by causing should_stop() to return True.

Causes step_fn to exit by raising an exception.

Raises:

StopIteration

run_with_hooks

run_with_hooks(
    *args,
    **kwargs
)

Same as MonitoredSession.run. Accepts the same arguments.