def testEvaluationLoopTimeout(self):
checkpoint_dir = os.path.join(self.get_temp_dir(),
'evaluation_loop_timeout')
if not gfile.Exists(checkpoint_dir):
gfile.MakeDirs(checkpoint_dir)
# We need a variable that that the saver will try to restore.
variables.get_or_create_global_step()
# Run with placeholders. If we actually try to evaluate this, we'd fail
# since we're not using a feed_dict.
cant_run_op = array_ops.placeholder(dtype=dtypes.float32)
start = time.time()
final_values = evaluation.evaluate_repeatedly(
checkpoint_dir=checkpoint_dir,
eval_ops=cant_run_op,
hooks=[evaluation.StopAfterNEvalsHook(10)],
timeout=6)
end = time.time()
self.assertFalse(final_values)
# Assert that we've waited for the duration of the timeout (minus the sleep
# time).
self.assertGreater(end - start, 5.0)
# Then the timeout kicked in and stops the loop.
self.assertLess(end - start, 7)
def testEvaluateWithEvalFeedDict(self):
# Create a checkpoint.
checkpoint_dir = os.path.join(self.get_temp_dir(),
'evaluate_with_eval_feed_dict')
self._train_model(checkpoint_dir, num_steps=1)
# We need a variable that that the saver will try to restore.
variables.get_or_create_global_step()
# Create a variable and an eval op that increments it with a placeholder.
my_var = variables.local_variable(0.0, name='my_var')
increment = array_ops.placeholder(dtype=dtypes.float32)
eval_ops = state_ops.assign_add(my_var, increment)
increment_value = 3
num_evals = 5
expected_value = increment_value * num_evals
final_values = evaluation.evaluate_repeatedly(
checkpoint_dir=checkpoint_dir,
eval_ops=eval_ops,
feed_dict={increment: 3},
final_ops={'my_var': array_ops.identity(my_var)},
hooks=[
evaluation.StopAfterNEvalsHook(num_evals),
],
max_number_of_evaluations=1)
self.assertEqual(final_values['my_var'], expected_value)
def testEvaluatePerfectModel(self):
checkpoint_dir = os.path.join(self.get_temp_dir(),
'evaluate_perfect_model_repeated')
# Train a Model to completion:
self._train_model(checkpoint_dir, num_steps=300)
# Run
inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
labels = constant_op.constant(self._labels, dtype=dtypes.float32)
logits = logistic_classifier(inputs)
predictions = math_ops.round(logits)
accuracy, update_op = metric_ops.streaming_accuracy(
predictions, labels)
final_values = evaluation.evaluate_repeatedly(
checkpoint_dir=checkpoint_dir,
eval_ops=update_op,
final_ops={'accuracy': accuracy},
hooks=[
evaluation.StopAfterNEvalsHook(1),
],
max_number_of_evaluations=1)
self.assertTrue(final_values['accuracy'] > .99)
def testEvalOpAndFinalOp(self):
checkpoint_dir = os.path.join(self.get_temp_dir(),
'eval_ops_and_final_ops')
# Train a model for a single step to get a checkpoint.
self._train_model(checkpoint_dir, num_steps=1)
checkpoint_path = evaluation.wait_for_new_checkpoint(checkpoint_dir)
# Create the model so we have something to restore.
inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
logistic_classifier(inputs)
num_evals = 5
final_increment = 9.0
my_var = variables.local_variable(0.0, name='MyVar')
eval_ops = state_ops.assign_add(my_var, 1.0)
final_ops = array_ops.identity(my_var) + final_increment
final_ops_values = evaluation.evaluate_once(
checkpoint_path=checkpoint_path,
eval_ops=eval_ops,
final_ops={'value': final_ops},
hooks=[
evaluation.StopAfterNEvalsHook(num_evals),
])
self.assertEqual(final_ops_values['value'],
num_evals + final_increment)
def testEvaluatePerfectModel(self):
checkpoint_dir = os.path.join(self.get_temp_dir(),
'evaluate_perfect_model_once')
# Train a Model to completion:
self._train_model(checkpoint_dir, num_steps=300)
# Run
inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
labels = constant_op.constant(self._labels, dtype=dtypes.float32)
logits = logistic_classifier(inputs)
predictions = math_ops.round(logits)
accuracy, update_op = metrics.accuracy(predictions=predictions,
labels=labels)
checkpoint_path = evaluation.wait_for_new_checkpoint(checkpoint_dir)
final_ops_values = evaluation.evaluate_once(
checkpoint_path=checkpoint_path,
eval_ops=update_op,
final_ops={'accuracy': accuracy},
hooks=[
evaluation.StopAfterNEvalsHook(1),
])
self.assertTrue(final_ops_values['accuracy'] > .99)
def testEvaluationLoopTimeoutWithTimeoutFn(self):
checkpoint_dir = os.path.join(
self.get_temp_dir(), 'evaluation_loop_timeout_with_timeout_fn')
# Train a Model to completion:
self._train_model(checkpoint_dir, num_steps=300)
# Run
inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
labels = constant_op.constant(self._labels, dtype=dtypes.float32)
logits = logistic_classifier(inputs)
predictions = math_ops.round(logits)
accuracy, update_op = metrics.accuracy(predictions=predictions,
labels=labels)
timeout_fn_calls = [0]
def timeout_fn():
timeout_fn_calls[0] += 1
return timeout_fn_calls[0] > 3
final_values = evaluation.evaluate_repeatedly(
checkpoint_dir=checkpoint_dir,
eval_ops=update_op,
final_ops={'accuracy': accuracy},
hooks=[
evaluation.StopAfterNEvalsHook(1),
],
eval_interval_secs=1,
max_number_of_evaluations=2,
timeout=0.1,
timeout_fn=timeout_fn)
# We should have evaluated once.
self.assertTrue(final_values['accuracy'] > .99)
# And called 4 times the timeout fn
self.assertEqual(4, timeout_fn_calls[0])
def evaluation_loop(master,
checkpoint_dir,
logdir,
num_evals=1,
initial_op=None,
initial_op_feed_dict=None,
init_fn=None,
eval_op=None,
eval_op_feed_dict=None,
final_op=None,
final_op_feed_dict=None,
summary_op=_USE_DEFAULT,
summary_op_feed_dict=None,
variables_to_restore=None,
eval_interval_secs=60,
max_number_of_evaluations=None,
session_config=None,
timeout=None,
timeout_fn=None,
hooks=None):
"""Runs TF-Slim's Evaluation Loop.
Args:
master: The BNS address of the TensorFlow master.
checkpoint_dir: The directory where checkpoints are stored.
logdir: The directory where the TensorFlow summaries are written to.
num_evals: The number of times to run `eval_op`.
initial_op: An operation run at the beginning of evaluation.
initial_op_feed_dict: A feed dictionary to use when executing `initial_op`.
init_fn: An optional callable to be executed after `init_op` is called. The
callable must accept one argument, the session being initialized.
eval_op: A operation run `num_evals` times.
eval_op_feed_dict: The feed dictionary to use when executing the `eval_op`.
final_op: An operation to execute after all of the `eval_op` executions. The
value of `final_op` is returned.
final_op_feed_dict: A feed dictionary to use when executing `final_op`.
summary_op: The summary_op to evaluate after running TF-Slims metric ops. By
default the summary_op is set to tf.compat.v1.summary.merge_all().
summary_op_feed_dict: An optional feed dictionary to use when running the
`summary_op`.
variables_to_restore: A list of TensorFlow variables to restore during
evaluation. If the argument is left as `None` then
slim.variables.GetVariablesToRestore() is used.
eval_interval_secs: The minimum number of seconds between evaluations.
max_number_of_evaluations: the max number of iterations of the evaluation.
If the value is left as 'None', the evaluation continues indefinitely.
session_config: An instance of `tf.compat.v1.ConfigProto` that will be used
to configure the `Session`. If left as `None`, the default will be used.
timeout: The maximum amount of time to wait between checkpoints. If left as
`None`, then the process will wait indefinitely.
timeout_fn: Optional function to call after a timeout. If the function
returns True, then it means that no new checkpoints will be generated and
the iterator will exit. The function is called with no arguments.
hooks: A list of additional `SessionRunHook` objects to pass during repeated
evaluations.
Returns:
The value of `final_op` or `None` if `final_op` is `None`.
"""
if summary_op == _USE_DEFAULT:
summary_op = summary.merge_all()
all_hooks = [
evaluation.StopAfterNEvalsHook(num_evals),
]
if summary_op is not None:
all_hooks.append(
evaluation.SummaryAtEndHook(log_dir=logdir,
summary_op=summary_op,
feed_dict=summary_op_feed_dict))
if hooks is not None:
# Add custom hooks if provided.
all_hooks.extend(hooks)
saver = None
if variables_to_restore is not None:
saver = tf_saver.Saver(variables_to_restore)
return evaluation.evaluate_repeatedly(
checkpoint_dir,
master=master,
scaffold=monitored_session.Scaffold(
init_op=initial_op,
init_feed_dict=initial_op_feed_dict,
init_fn=init_fn,
saver=saver),
eval_ops=eval_op,
feed_dict=eval_op_feed_dict,
final_ops=final_op,
final_ops_feed_dict=final_op_feed_dict,
eval_interval_secs=eval_interval_secs,
hooks=all_hooks,
config=session_config,
max_number_of_evaluations=max_number_of_evaluations,
timeout=timeout,
timeout_fn=timeout_fn)
def evaluate_once(master,
checkpoint_path,
logdir,
num_evals=1,
initial_op=None,
initial_op_feed_dict=None,
eval_op=None,
eval_op_feed_dict=None,
final_op=None,
final_op_feed_dict=None,
summary_op=_USE_DEFAULT,
summary_op_feed_dict=None,
variables_to_restore=None,
session_config=None,
hooks=None):
"""Evaluates the model at the given checkpoint path.
Args:
master: The BNS address of the TensorFlow master.
checkpoint_path: The path to a checkpoint to use for evaluation.
logdir: The directory where the TensorFlow summaries are written to.
num_evals: The number of times to run `eval_op`.
initial_op: An operation run at the beginning of evaluation.
initial_op_feed_dict: A feed dictionary to use when executing `initial_op`.
eval_op: A operation run `num_evals` times.
eval_op_feed_dict: The feed dictionary to use when executing the `eval_op`.
final_op: An operation to execute after all of the `eval_op` executions. The
value of `final_op` is returned.
final_op_feed_dict: A feed dictionary to use when executing `final_op`.
summary_op: The summary_op to evaluate after running TF-Slims metric ops. By
default the summary_op is set to tf.compat.v1.summary.merge_all().
summary_op_feed_dict: An optional feed dictionary to use when running the
`summary_op`.
variables_to_restore: A list of TensorFlow variables to restore during
evaluation. If the argument is left as `None` then
slim.variables.GetVariablesToRestore() is used.
session_config: An instance of `tf.compat.v1.ConfigProto` that will be used
to configure the `Session`. If left as `None`, the default will be used.
hooks: A list of additional `SessionRunHook` objects to pass during the
evaluation.
Returns:
The value of `final_op` or `None` if `final_op` is `None`.
"""
if summary_op == _USE_DEFAULT:
summary_op = summary.merge_all()
all_hooks = [
evaluation.StopAfterNEvalsHook(num_evals),
]
if summary_op is not None:
all_hooks.append(
evaluation.SummaryAtEndHook(log_dir=logdir,
summary_op=summary_op,
feed_dict=summary_op_feed_dict))
if hooks is not None:
all_hooks.extend(hooks)
saver = None
if variables_to_restore is not None:
saver = tf_saver.Saver(variables_to_restore)
return evaluation.evaluate_once(checkpoint_path,
master=master,
scaffold=monitored_session.Scaffold(
init_op=initial_op,
init_feed_dict=initial_op_feed_dict,
saver=saver),
eval_ops=eval_op,
feed_dict=eval_op_feed_dict,
final_ops=final_op,
final_ops_feed_dict=final_op_feed_dict,
hooks=all_hooks,
config=session_config)
def evaluation_loop(master,
checkpoint_dir,
logdir,
num_evals=1,
initial_op=None,
initial_op_feed_dict=None,
eval_op=None,
eval_op_feed_dict=None,
final_op=None,
final_op_feed_dict=None,
summary_op=_USE_DEFAULT,
summary_op_feed_dict=None,
variables_to_restore=None,
eval_interval_secs=60,
max_number_of_evaluations=None,
session_config=None,
timeout=None):
"""Runs TF-Slim's Evaluation Loop.
Args:
master: The BNS address of the TensorFlow master.
checkpoint_dir: The directory where checkpoints are stored.
logdir: The directory where the TensorFlow summaries are written to.
num_evals: The number of times to run `eval_op`.
initial_op: An operation run at the beginning of evaluation.
initial_op_feed_dict: A feed dictionary to use when executing `initial_op`.
eval_op: A operation run `num_evals` times.
eval_op_feed_dict: The feed dictionary to use when executing the `eval_op`.
final_op: An operation to execute after all of the `eval_op` executions. The
value of `final_op` is returned.
final_op_feed_dict: A feed dictionary to use when executing `final_op`.
summary_op: The summary_op to evaluate after running TF-Slims metric ops. By
default the summary_op is set to tf.summary.merge_all().
summary_op_feed_dict: An optional feed dictionary to use when running the
`summary_op`.
variables_to_restore: A list of TensorFlow variables to restore during
evaluation. If the argument is left as `None` then
slim.variables.GetVariablesToRestore() is used.
eval_interval_secs: The minimum number of seconds between evaluations.
max_number_of_evaluations: the max number of iterations of the evaluation.
If the value is left as 'None', the evaluation continues indefinitely.
session_config: An instance of `tf.ConfigProto` that will be used to
configure the `Session`. If left as `None`, the default will be used.
timeout: The maximum amount of time to wait between checkpoints. If left as
`None`, then the process will wait indefinitely.
Returns:
The value of `final_op` or `None` if `final_op` is `None`.
"""
if summary_op == _USE_DEFAULT:
summary_op = summary.merge_all()
hooks = [
evaluation.StopAfterNEvalsHook(num_evals),
]
if summary_op is not None:
hooks.append(
evaluation.SummaryAtEndHook(logdir, summary_op,
summary_op_feed_dict))
return evaluation.evaluate_repeatedly(
checkpoint_dir,
master=master,
scaffold=monitored_session.Scaffold(
init_op=initial_op, init_feed_dict=initial_op_feed_dict),
eval_ops=eval_op,
feed_dict=eval_op_feed_dict,
final_ops=final_op,
final_ops_feed_dict=final_op_feed_dict,
variables_to_restore=variables_to_restore,
eval_interval_secs=eval_interval_secs,
hooks=hooks,
config=session_config,
max_number_of_evaluations=max_number_of_evaluations,
timeout=timeout)
