def test_estimator(script_mode):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
with SagemakerSimulator() as sim:
# Setup
mnist_classifier = get_estimator()
train_input_fn, eval_input_fn = get_input_fns()
# Train and evaluate
train_steps, eval_steps = 80, 20
if script_mode:
hook = smd.EstimatorHook(out_dir=sim.out_dir)
hook.set_mode(mode=smd.modes.TRAIN)
mnist_classifier.train(input_fn=train_input_fn,
steps=train_steps,
hooks=[hook])
hook.set_mode(mode=smd.modes.EVAL)
mnist_classifier.evaluate(input_fn=eval_input_fn,
steps=eval_steps,
hooks=[hook])
else:
mnist_classifier.train(input_fn=train_input_fn, steps=train_steps)
mnist_classifier.evaluate(input_fn=eval_input_fn, steps=eval_steps)
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
print(trial)
assert smd.get_hook() is not None, "Hook was not created."
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert trial.steps() == [0, train_steps], "Wrong step count for trial."
def test_estimator(out_dir, tf_eager_mode, saveall):
""" Works as intended. """
if tf_eager_mode is False:
tf.compat.v1.disable_eager_execution()
tf.compat.v1.reset_default_graph()
tf.keras.backend.clear_session()
mnist_classifier = get_estimator()
train_input_fn, eval_input_fn = get_input_fns()
# Train and evaluate
train_steps, eval_steps = 8, 2
hook = smd.EstimatorHook(out_dir=out_dir, save_all=saveall)
hook.set_mode(mode=smd.modes.TRAIN)
mnist_classifier.train(input_fn=train_input_fn, steps=train_steps, hooks=[hook])
hook.set_mode(mode=smd.modes.EVAL)
mnist_classifier.evaluate(input_fn=eval_input_fn, steps=eval_steps, hooks=[hook])
# Check that hook created and tensors saved
trial = smd.create_trial(path=out_dir)
tnames = trial.tensor_names()
assert len(trial.steps()) > 0
if saveall:
# Number of tensors in each collection
# vanilla TF 2.2: all = 300, loss = 1, weights = 4, gradients = 0, biases = 18, optimizer variables = 0, metrics = 0, others = 277
# AWS-TF 2.2 : all = 300, loss = 1, weights = 4, gradients = 8, biases = 18, optimizer variables = 0, metrics = 0, others = 269
# AWS-TF 2.1 : all = 309, loss = 1, weights = 4, gradients = 8, biases = 18, optimizer variables = 0, metrics = 0, others = 278
assert len(tnames) >= 300
assert len(trial.tensor_names(collection=CollectionKeys.LOSSES)) == 1
assert len(trial.tensor_names(collection=CollectionKeys.WEIGHTS)) == 4
assert len(trial.tensor_names(collection=CollectionKeys.BIASES)) == 18
assert len(trial.tensor_names(collection=CollectionKeys.GRADIENTS)) >= 0
assert len(trial.tensor_names(collection=CollectionKeys.OPTIMIZER_VARIABLES)) >= 0
else:
assert len(tnames) == 1
assert len(trial.tensor_names(collection=CollectionKeys.LOSSES)) == 1
def helper_train(script_mode=False, sim=None, train_steps=80, eval_steps=20):
# Setup
mnist_classifier = get_estimator()
train_input_fn, eval_input_fn = get_input_fns()
# Train and evaluate
if script_mode:
hook = smd.EstimatorHook(out_dir=sim.out_dir)
hook.set_mode(mode=smd.modes.TRAIN)
mnist_classifier.train(input_fn=train_input_fn, steps=train_steps, hooks=[hook])
hook.set_mode(mode=smd.modes.EVAL)
mnist_classifier.evaluate(input_fn=eval_input_fn, steps=eval_steps, hooks=[hook])
else:
mnist_classifier.train(input_fn=train_input_fn, steps=train_steps)
mnist_classifier.evaluate(input_fn=eval_input_fn, steps=eval_steps)
def helper_test_estimator_gradients_zcc(nested=False, mirrored=False):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/opt/ml/output/tensors",
"HookParameters" : {
"save_interval": "2",
"include_workers": "all"
},
"CollectionConfigurations": [
{
"CollectionName": "gradients"
},
{
"CollectionName": "weights"
},
{
"CollectionName": "losses"
},
{
"CollectionName": "biases"
}
]
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
if mirrored:
test_basic("/opt/ml/output/tensors", zcc=True)
else:
# Setup
mnist_classifier = get_estimator(nested_optimizer=nested,
mirrored=mirrored)
train_input_fn, eval_input_fn = get_input_fns()
# Train and evaluate
train_steps, eval_steps = 10, 10
mnist_classifier.train(input_fn=train_input_fn, steps=train_steps)
mnist_classifier.evaluate(input_fn=eval_input_fn, steps=eval_steps)
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
print(trial)
assert smd.get_hook() is not None, "Hook was not created."
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert trial.steps() == [
0,
2,
4,
6,
8,
10,
12,
14,
16,
18,
], "Wrong step count for trial."
print(trial.tensor_names(collection="gradients"))
assert len(trial.tensor_names(collection="gradients")) > 0
assert len(trial.tensor_names(collection="weights")) > 0
assert len(trial.tensor_names(collection="losses")) > 0
assert len(
trial.tensor(
trial.tensor_names(collection="gradients")[0]).steps()) > 0
assert len(trial.modes()) == 2