tf.estimator.ProfilerHook

Captures CPU/GPU profiling information every N steps or seconds.

Inherits From: SessionRunHook

This produces files called "timeline-.json", which are in Chrome Trace format.

For more information see: https://github.com/catapult-project/catapult/blob/master/tracing/README.md

save_steps int, save profile traces every N steps. Exactly one of save_secs and save_steps should be set.
save_secs int or float, save profile traces every N seconds.
output_dir string, the directory to save the profile traces to. Defaults to the current directory.
show_dataflow bool, if True, add flow events to the trace connecting producers and consumers of tensors.
show_memory bool, if True, add object snapshot events to the trace showing the sizes and lifetimes of tensors.

Methods

after_create_session

View source

Called when new TensorFlow session is created.

This is called to signal the hooks that a new session has been created. This has two essential differences with the situation in which begin is called:

  • When this is called, the graph is finalized and ops can no longer be added to the graph.
  • This method will also be called as a result of recovering a wrapped session, not only at the beginning of the overall session.

Args
session A TensorFlow Session that has been created.
coord A Coordinator object which keeps track of all threads.

after_run

View source

Called after each call to run().

The run_values argument contains results of requested ops/tensors by before_run().

The run_context argument is the same one send to before_run call. run_context.request_stop() can be called to stop the iteration.

If session.run() raises any exceptions then after_run() is not called.

Args
run_context A SessionRunContext object.
run_values A SessionRunValues object.

before_run

View source

Called before each call to run().

You can return from this call a SessionRunArgs object indicating ops or tensors to add to the upcoming run() call. These ops/tensors will be run together with the ops/tensors originally passed to the original run() call. The run args you return can also contain feeds to be added to the run() call.

The run_context argument is a SessionRunContext that provides information about the upcoming run() call: the originally requested op/tensors, the TensorFlow Session.

At this point graph is finalized and you can not add ops.

Args
run_context A SessionRunContext object.

Returns
None or a SessionRunArgs object.

begin

View source

Called once before using the session.

When called, the default graph is the one that will be launched in the session. The hook can modify the graph by adding new operations to it. After the begin(