def test_monitored_session(script_mode):
""" 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": "100"
}
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
train_op, X, Y = get_train_op_and_placeholders()
init = tf.global_variables_initializer()
mnist = get_data()
if script_mode:
hook = smd.SessionHook(out_dir=sim.out_dir)
sess = tf.train.MonitoredSession(hooks=[hook])
else:
sess = tf.train.MonitoredSession()
with sess:
sess.run(init)
for step in range(1, 101):
batch_x, batch_y = mnist.train.next_batch(32)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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."
def test_keras_gradients(script_mode, tf_optimizer):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
tf.keras.backend.clear_session()
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/opt/ml/output/tensors",
"CollectionConfigurations": [
{
"CollectionName": "gradients"
},
{
"CollectionName": "optimizer_variables"
},
{
"CollectionName": "losses"
}
]
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
model = get_keras_model_v1()
(x_train, y_train), (x_test, y_test) = get_keras_data()
if tf_optimizer:
opt = tf.train.RMSPropOptimizer(0.1)
else:
opt = tf.keras.optimizers.RMSprop()
if script_mode:
hook = smd.KerasHook(
out_dir=sim.out_dir,
include_collections=["gradients", "optimizer_variables", "losses"],
)
opt = hook.wrap_optimizer(opt)
model.compile(
loss="sparse_categorical_crossentropy", optimizer=opt, metrics=["accuracy"]
)
history = model.fit(
x_train, y_train, batch_size=16, epochs=5, validation_split=0.2, callbacks=[hook]
)
test_scores = model.evaluate(x_test, y_test, verbose=2, callbacks=[hook])
else:
model.compile(
loss="sparse_categorical_crossentropy", optimizer=opt, metrics=["accuracy"]
)
history = model.fit(x_train, y_train, batch_size=16, epochs=5, validation_split=0.2)
test_scores = model.evaluate(x_test, y_test, verbose=2)
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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 len(trial.tensor_names(collection="gradients")) > 0
if not tf_optimizer:
# as this is only supported for keras optimizers currently
assert len(trial.tensor_names(collection="optimizer_variables")) > 0
def test_linear_classifier(script_mode: bool):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
with SagemakerSimulator() as sim:
# Setup
train_input_fn, eval_input_fn = get_input_fns()
x_feature = tf.feature_column.numeric_column("x", shape=(28, 28))
estimator = tf.compat.v1.estimator.LinearClassifier(
feature_columns=[x_feature],
model_dir="/tmp/mnist_linear_classifier",
n_classes=10)
# Train
if script_mode:
hook = smd.EstimatorHook(out_dir=sim.out_dir)
estimator.train(input_fn=train_input_fn, steps=100, hooks=[hook])
else:
estimator.train(input_fn=train_input_fn, steps=100)
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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."
def test_keras_v1(script_mode):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
tf.keras.backend.clear_session()
with SagemakerSimulator() as sim:
model = get_keras_model_v1()
(x_train, y_train), (x_test, y_test) = get_keras_data()
model.compile(
loss="sparse_categorical_crossentropy",
optimizer=tf.keras.optimizers.RMSprop(),
metrics=["accuracy"],
)
if script_mode:
hook = smd.KerasHook(out_dir=sim.out_dir)
history = model.fit(
x_train, y_train, batch_size=64, epochs=5, validation_split=0.2, callbacks=[hook]
)
test_scores = model.evaluate(x_test, y_test, verbose=2, callbacks=[hook])
else:
history = model.fit(x_train, y_train, batch_size=64, epochs=5, validation_split=0.2)
test_scores = model.evaluate(x_test, y_test, verbose=2)
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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."
def test_estimator(script_mode: bool):
""" 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_tensorboard_dir_sagemaker():
""" In Sagemaker, we read the tensorboard_dir from a separate JSON config file. """
with SagemakerSimulator() as sim:
smd.del_hook()
hook = smd.get_hook(create_if_not_exists=True)
assert hook.out_dir == sim.out_dir
assert hook.tensorboard_dir == sim.tensorboard_dir
def test_monitored_session(script_mode: bool):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
with SagemakerSimulator() as sim:
train_op, X, Y = get_train_op_and_placeholders()
init = tf.compat.v1.global_variables_initializer()
mnist = get_data()
if script_mode:
hook = smd.SessionHook(out_dir=sim.out_dir)
sess = tf.train.MonitoredSession(hooks=[hook])
else:
sess = tf.train.MonitoredSession()
with sess:
sess.run(init)
for step in range(1, 101):
batch_x, batch_y = mnist.train.next_batch(32)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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."
def helper_test_keras_v2(script_mode: bool = False, eager_mode: bool = True):
""" Test the default ZCC behavior of saving losses and metrics in eager and non-eager modes."""
smd.del_hook()
tf.keras.backend.clear_session()
if not eager_mode:
tf.compat.v1.disable_eager_execution()
with SagemakerSimulator() as sim:
model = get_keras_model_v2()
(x_train, y_train), (x_test, y_test) = get_keras_data()
x_train, x_test = x_train / 255, x_test / 255
opt = tf.keras.optimizers.RMSprop()
if script_mode:
hook = smd.KerasHook(out_dir=sim.out_dir, export_tensorboard=True)
opt = hook.wrap_optimizer(opt)
model.compile(loss="sparse_categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
history = model.fit(x_train,
y_train,
batch_size=64,
epochs=2,
validation_split=0.2,
callbacks=[hook])
test_scores = model.evaluate(x_test,
y_test,
verbose=2,
callbacks=[hook])
else:
model.compile(loss="sparse_categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
history = model.fit(x_train,
y_train,
batch_size=64,
epochs=2,
validation_split=0.2)
test_scores = model.evaluate(x_test, y_test, verbose=2)
hook = smd.get_hook()
assert hook
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
# DEFAULT TENSORS SAVED
assert len(trial.tensor_names(
collection=CollectionKeys.LOSSES)) > 0, "No Losses Saved"
assert len(trial.tensor_names(
collection=CollectionKeys.METRICS)) > 0, "No Metrics Saved"
assert (len(trial.tensor_names(collection=CollectionKeys.WEIGHTS)) == 0
), "Weights were not expected to be saved by default"
assert (len(trial.tensor_names(collection=CollectionKeys.BIASES)) == 0
), "Biases were not expected to be saved by default"
def helper_test_keras_v2_json_config(json_file_contents,
script_mode: bool = False,
eager_mode: bool = True):
""" Tests ZCC with custom hook configs """
smd.del_hook()
tf.keras.backend.clear_session()
if not eager_mode:
tf.compat.v1.disable_eager_execution()
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
model = get_keras_model_v2()
(x_train, y_train), (x_test, y_test) = get_keras_data()
x_train, x_test = x_train / 255, x_test / 255
opt = tf.keras.optimizers.RMSprop()
if script_mode:
hook = smd.KerasHook.create_from_json_file()
opt = hook.wrap_optimizer(opt)
model.compile(loss="sparse_categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
history = model.fit(x_train,
y_train,
batch_size=64,
epochs=2,
validation_split=0.2,
callbacks=[hook])
test_scores = model.evaluate(x_test,
y_test,
verbose=2,
callbacks=[hook])
else:
model.compile(loss="sparse_categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
history = model.fit(x_train,
y_train,
epochs=2,
batch_size=64,
validation_split=0.2)
test_scores = model.evaluate(x_test, y_test, verbose=2)
hook = smd.get_hook()
assert hook
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
if not eager_mode:
assert len(trial.tensor_names(collection="gradients")) > 0
assert len(trial.tensor_names(collection="weights")) > 0
assert len(trial.tensor_names(collection="losses")) > 0
def test_keras_to_estimator(script_mode):
""" Works as intended. """
import tensorflow.compat.v1.keras as keras
tf.reset_default_graph()
smd.del_hook()
keras.backend.clear_session()
with SagemakerSimulator() as sim:
model = keras.models.Sequential([
keras.layers.Dense(16, activation="relu", input_shape=(4, )),
keras.layers.Dropout(0.2),
keras.layers.Dense(1, activation="sigmoid"),
])
def input_fn():
split = tfds.Split.TRAIN
data_dir = TEST_DATASET_S3_PATH if use_s3_datasets() else None
dataset = tfds.load("iris",
data_dir=data_dir,
split=split,
as_supervised=True)
dataset = dataset.map(lambda features, labels:
({
"dense_input": features
}, labels))
dataset = dataset.batch(32).repeat()
return dataset
model.compile(loss="categorical_crossentropy", optimizer="adam")
model.summary()
keras_estimator = tf.keras.estimator.model_to_estimator(
keras_model=model, model_dir=sim.out_dir)
if script_mode:
hook = smd.EstimatorHook(sim.out_dir)
hook.set_mode(smd.modes.TRAIN)
keras_estimator.train(input_fn=input_fn, steps=25, hooks=[hook])
hook.set_mode(smd.modes.EVAL)
eval_result = keras_estimator.evaluate(input_fn=input_fn,
steps=10,
hooks=[hook])
else:
keras_estimator.train(input_fn=input_fn, steps=25)
keras_estimator.evaluate(input_fn=input_fn, steps=10)
tr = smd.create_trial(sim.out_dir)
assert len(tr.tensor_names()) == 1
assert tr.steps() == [0, 25]
assert len(tr.steps(smd.modes.TRAIN)) == 1
assert len(tr.steps(smd.modes.EVAL)) == 1
def test_temp_paths():
with SagemakerSimulator() as sim:
for path in [
"/opt/ml/output/tensors/events/a",
"/opt/ml/output/tensors/a",
"/opt/ml/output/tensors/events/a/b",
]:
temp_path = get_temp_path(path)
assert temp_path.endswith(SMDEBUG_TEMP_PATH_SUFFIX)
with ScriptSimulator() as sim:
for path in ["/a/b/c", "/opt/ml/output/a", "a/b/c"]:
temp_path = get_temp_path(path)
assert temp_path.endswith(SMDEBUG_TEMP_PATH_SUFFIX)
def helper_test_keras_v2_gradienttape(script_mode: bool = False,
json_file_contents="{}",
default=False):
""" Test the default ZCC behavior of saving losses and metrics in eager and non-eager modes."""
smd.del_hook()
tf.keras.backend.clear_session()
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
helper_keras_gradienttape_train(script_mode=script_mode,
json_file_contents=json_file_contents,
sim=sim)
hook = smd.get_hook()
if script_mode:
assert hook
if default:
assert hook.has_default_hook_configuration()
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert len(trial.tensor_names(collection="losses")) > 0
else:
if version.parse(tf.__version__) < version.parse("2.1.2"):
assert not hook # only supported on TF 2.1.2 and greater
return
assert hook
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert len(trial.tensor_names(collection="losses")) > 0
if is_tf_2_2() and default is False:
# Inputs and Outputs are not saved with the default collection configurations.
assert len(trial.tensor_names(collection="inputs")) > 0
assert len(trial.tensor_names(collection="outputs")) > 0
assert trial.tensor_names(collection="outputs") == [
"predictions"
]
if "dense_layers" in json_file_contents:
# Only assert for test_keras_v2_multi_collections
# which defines this custom collection
assert len(
trial.tensor_names(collection="dense_layers")) > 0
else:
assert len(
trial.tensor_names(collection="dense_layers")) == 0
def test_temp_paths():
with SagemakerSimulator() as sim:
for path in [
"/opt/ml/output/tensors/events/a",
"/opt/ml/output/tensors/a",
"/opt/ml/output/tensors/events/a/b",
]:
temp_path = get_temp_path(path)
assert temp_path.endswith(SAGEMAKER_TEMP_PATH_SUFFIX)
assert not temp_path.startswith(NON_SAGEMAKER_TEMP_PATH_PREFIX)
with ScriptSimulator() as sim:
for path in ["/a/b/c", "/opt/ml/output/a", "a/b/c"]:
temp_path = get_temp_path(path)
assert not SAGEMAKER_TEMP_PATH_SUFFIX in temp_path
assert temp_path.startswith(NON_SAGEMAKER_TEMP_PATH_PREFIX)
def test_estimator(script_mode):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
with SagemakerSimulator() as sim:
train_steps, eval_steps = 80, 20
helper_train(
script_mode=script_mode, sim=sim, train_steps=train_steps, eval_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_outdir_sagemaker(monkeypatch):
with TemporaryDirectory() as dir_name:
json_file_contents = f"""
{{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "{dir_name}",
"HookParameters" : {{
"save_interval": "2",
"include_workers": "all"
}}
}}
"""
from smdebug.tensorflow import get_hook
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
hook = get_hook("keras", create_if_not_exists=True)
assert hook.out_dir == dir_name
def test_keras_gradients_mirrored(include_workers="one"):
""" Works as intended. """
smd.del_hook()
tf.reset_default_graph()
tf.keras.backend.clear_session()
json_file_contents_p1 = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/opt/ml/output/tensors",
"HookParameters" : {
"""
json_file_contents_p2 = f'"include_workers": "{include_workers}",'
json_file_contents_p3 = """
"save_interval": "3"
},
"CollectionConfigurations": [
{
"CollectionName": "gradients"
},
{
"CollectionName": "optimizer_variables"
},
{
"CollectionName": "losses"
},
{
"CollectionName": "weights"
},
{
"CollectionName": "biases"
},
{
"CollectionName": "outputs"
},
{
"CollectionName": "metrics"
}
]
}
"""
json_file_contents = json_file_contents_p1 + json_file_contents_p2 + json_file_contents_p3
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
test_tf_keras("/opt/ml/output/tensors",
zcc=True,
include_workers=include_workers)
def test_json_params_sagemaker():
with SagemakerSimulator() as sim:
params_dict = get_json_config_as_dict(
json_config_path="tests/core/json_configs/all_params.json")
hook_params = collect_hook_config_params(params_dict)
include_collections = get_include_collections(params_dict)
coll_manager = CollectionManager()
add_collections_to_manager(coll_manager, params_dict, hook_params)
assert hook_params["include_workers"] == "one"
assert hook_params["save_all"] is True
assert coll_manager.get("weights").save_histogram is False
assert coll_manager.get("gradients").save_histogram is False
assert "weights" in include_collections
assert "gradients" in include_collections
assert len(include_collections) == 2
assert hook_params["export_tensorboard"] == True
assert hook_params["tensorboard_dir"] == sim.tensorboard_dir
def test_integration_mxnet():
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/tmp/mxnet_integ_test",
"CollectionConfigurations": [
{
"CollectionName": "losses",
"CollectionParameters": {
"save_interval": 100
}
}
]
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as _:
train_model()
validate()
def test_integration_mxnet():
# DEFAULT CONSTANTS
batch_size = 256
epochs = 1
learning_rate = 0.1
mx.random.seed(128)
random.seed(12)
np.random.seed(2)
context = mx.cpu()
# Create a Gluon Model.
net = create_gluon_model()
# Start the training.
train_data, val_data = prepare_data(batch_size)
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/tmp/mxnet_integ_test",
"CollectionConfigurations": [
{
"CollectionName": "losses",
"CollectionParameters": {
"save_interval": 100
}
}
]
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
train_model(
net=net,
epochs=epochs,
ctx=context,
learning_rate=learning_rate,
momentum=0.9,
train_data=train_data,
val_data=val_data,
)
validate()
def main():
opt = parse_args()
mx.random.seed(128)
random.seed(12)
np.random.seed(2)
context = mx.cpu() if opt.context.lower() == "cpu" else mx.gpu()
# Create a Gluon Model.
net = create_gluon_model()
# Start the training.
train_data, val_data = prepare_data(opt.batch_size)
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/tmp/mxnet_integ_test",
"CollectionConfigurations": [
{
"CollectionName": "losses",
"CollectionParameters": {
"save_interval": 100
}
}
]
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
train_model(
net=net,
epochs=opt.epochs,
ctx=context,
learning_rate=opt.learning_rate,
momentum=0.9,
train_data=train_data,
val_data=val_data,
)
if opt.validate:
validate()
def test_monitored_session_gradients_zcc():
""" Works as intended. """
smd.del_hook()
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/opt/ml/output/tensors",
"CollectionConfigurations": [
{
"CollectionName": "gradients"
},
{
"CollectionName": "losses"
}
]
}
"""
tf.reset_default_graph()
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
train_op, X, Y = get_train_op_and_placeholders()
init = tf.compat.v1.global_variables_initializer()
mnist = get_data()
sess = tf.train.MonitoredSession()
with sess:
sess.run(init)
for step in range(1, 101):
batch_x, batch_y = mnist.train.next_batch(32)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
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 len(trial.tensor_names(collection="gradients")) > 0
def test_sagemaker():
json_file_contents = """
{
"S3OutputPath": "s3://sagemaker-test",
"LocalPath": "/opt/ml/output/tensors",
"HookParameters": null,
"CollectionConfigurations": [
{
"CollectionName": "weights",
"CollectionParameters": null
},
{
"CollectionName": "losses",
"CollectionParameters": null
}
],
"DebugHookSpecification": null
}
"""
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
smd.del_hook()
hook = smd.get_hook(hook_type="session", create_if_not_exists=True)
print(hook)
assert "weights" in hook.include_collections, hook
def 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
def helper_test_keras_v2_gradienttape(script_mode: bool = False,
json_file_contents="{}",
default=False):
""" Test the default ZCC behavior of saving losses and metrics in eager and non-eager modes."""
smd.del_hook()
tf.keras.backend.clear_session()
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28,
1)), # WA for TF issue #36279
tf.keras.layers.Dense(128, activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation="softmax"),
])
(x_train, y_train), _ = get_keras_data()
dataset = tf.data.Dataset.from_tensor_slices(
(tf.cast(x_train[..., tf.newaxis] / 255,
tf.float32), tf.cast(y_train, tf.int64)))
dataset = dataset.shuffle(1000).batch(64)
opt = tf.keras.optimizers.RMSprop()
cce = tf.keras.losses.CategoricalCrossentropy(from_logits=True)
train_acc_metric = tf.keras.metrics.SparseCategoricalAccuracy()
n_epochs = 1
if script_mode:
if json_file_contents == "{}":
hook = smd.KerasHook(out_dir=sim.out_dir,
export_tensorboard=True)
else:
hook = smd.KerasHook.create_from_json_file()
for epoch in range(n_epochs):
print("Epoch %d/%d" % (epoch + 1, n_epochs))
for data, labels in dataset:
dataset_labels = labels
labels = tf.one_hot(labels, depth=10)
with hook.wrap_tape(tf.GradientTape()) as tape:
logits = model(data, training=True) # (32,10)
loss_value = cce(labels, logits)
grads = tape.gradient(loss_value, model.variables)
opt.apply_gradients(zip(grads, model.variables))
acc = train_acc_metric(dataset_labels, logits)
hook.save_tensor(tensor_name="accuracy",
tensor_value=acc,
collections_to_write="metrics")
log = "Epoch %d " % (epoch + 1)
log += "Accuracy %.4f" % train_acc_metric.result()
print(log)
train_acc_metric.reset_states()
hook = smd.get_hook()
assert hook
if default:
assert hook.has_default_hook_configuration()
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert len(trial.tensor_names(collection="losses")) > 0
else:
# ZCC support added from smdebug v0.8.0)
for epoch in range(n_epochs):
print("Epoch %d/%d" % (epoch + 1, n_epochs))
for data, labels in dataset:
dataset_labels = labels
labels = tf.one_hot(labels, depth=10)
with tf.GradientTape(persistent=True) as tape:
logits = model(data, training=True) # (32,10)
loss_value = cce(labels, logits)
grads = tape.gradient(loss_value, model.variables)
opt.apply_gradients(zip(grads, model.variables))
acc = train_acc_metric(dataset_labels, logits)
log = "Epoch %d " % (epoch + 1)
log += "Accuracy %.4f" % train_acc_metric.result()
print(log)
train_acc_metric.reset_states()
hook = smd.get_hook()
if not (is_tf_2_2() or is_tf_2_3()):
assert not hook # only supported on TF 2.2 and greater
return
assert hook
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert len(trial.tensor_names(collection="losses")) > 0
if is_tf_2_2() and default is False:
# Inputs and Outputs are not saved with the default collection configurations.
assert len(trial.tensor_names(collection="inputs")) > 0
assert len(trial.tensor_names(collection="outputs")) > 0
assert trial.tensor_names(collection="outputs") == [
"predictions"
]
if "dense_layers" in json_file_contents:
# Only assert for test_keras_v2_multi_collections
# which defines this custom collection
assert len(
trial.tensor_names(collection="dense_layers")) > 0
else:
assert len(
trial.tensor_names(collection="dense_layers")) == 0
def helper_test_keras_v2_gradienttape(script_mode: bool = False,
json_file_contents="{}"):
""" Test the default ZCC behavior of saving losses and metrics in eager and non-eager modes."""
smd.del_hook()
tf.keras.backend.clear_session()
with SagemakerSimulator(json_file_contents=json_file_contents) as sim:
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28,
1)), # WA for TF issue #36279
tf.keras.layers.Dense(128, activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation="softmax"),
])
(x_train, y_train), _ = get_keras_data()
dataset = tf.data.Dataset.from_tensor_slices(
(tf.cast(x_train[..., tf.newaxis] / 255,
tf.float32), tf.cast(y_train, tf.int64)))
dataset = dataset.shuffle(1000).batch(64)
opt = tf.keras.optimizers.RMSprop()
cce = tf.keras.losses.CategoricalCrossentropy(from_logits=True)
train_acc_metric = tf.keras.metrics.SparseCategoricalAccuracy()
n_epochs = 2
if script_mode:
if json_file_contents == "{}":
hook = smd.KerasHook(out_dir=sim.out_dir,
export_tensorboard=True)
else:
hook = smd.KerasHook.create_from_json_file()
for epoch in range(n_epochs):
print("Epoch %d/%d" % (epoch + 1, n_epochs))
for data, labels in dataset:
dataset_labels = labels
labels = tf.one_hot(labels, depth=10)
with hook.wrap_tape(tf.GradientTape()) as tape:
logits = model(data, training=True) # (32,10)
loss_value = cce(labels, logits)
grads = tape.gradient(loss_value, model.variables)
opt.apply_gradients(zip(grads, model.variables))
acc = train_acc_metric(dataset_labels, logits)
hook.record_tensor_value(tensor_name="accuracy",
tensor_value=acc)
log = "Epoch %d " % (epoch + 1)
log += "Accuracy %.4f" % train_acc_metric.result()
print(log)
train_acc_metric.reset_states()
hook = smd.get_hook()
assert hook
hook.close()
# Check that hook created and tensors saved
trial = smd.create_trial(path=sim.out_dir)
assert len(trial.steps()) > 0, "Nothing saved at any step."
assert len(trial.tensor_names()) > 0, "Tensors were not saved."
assert len(trial.tensor_names(collection="losses")) > 0
else:
# ZCC doesn't support yet (as of smdebug v0.7.2)
for epoch in range(n_epochs):
print("Epoch %d/%d" % (epoch + 1, n_epochs))
for data, labels in dataset:
dataset_labels = labels
labels = tf.one_hot(labels, depth=10)
with tf.GradientTape(persistent=True) as tape:
logits = model(data, training=True) # (32,10)
loss_value = cce(labels, logits)
grads = tape.gradient(loss_value, model.variables)
opt.apply_gradients(zip(grads, model.variables))
acc = train_acc_metric(dataset_labels, logits)
log = "Epoch %d " % (epoch + 1)
log += "Accuracy %.4f" % train_acc_metric.result()
print(log)
train_acc_metric.reset_states()
hook = smd.get_hook()
assert not hook
