OSSForks/tensorflow
1
0
Fork 0
mirror of https://github.com/zebrajr/tensorflow.git synced 2026-01-15 12:15:41 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Add unit test for model_to_estimator where inpu_fn

Browse Source 
returns features and labels as a list instead of dict.

PiperOrigin-RevId: 212685344
This commit is contained in:
Zhenyu Tan
2018-09-12 12:33:24 -07:00
committed by TensorFlower Gardener
parent 28e945e590
commit 3fb474713b
3 changed files with 246 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
tensorflow/contrib/distribute/python/keras_test.py
View File

@@ -34,6 +34,7 @@ from tensorflow.python.framework import dtypes
from tensorflow.python.framework import test_util
from tensorflow.python.keras import testing_utils
from tensorflow.python.keras.engine import distributed_training_utils
from tensorflow.python.ops.parsing_ops import gen_parsing_ops
from tensorflow.python.platform import gfile
from tensorflow.python.platform import test
from tensorflow.python.summary.writer import writer_cache
@@ -66,6 +67,32 @@ def simple_functional_model():
return model
def multi_inputs_multi_outputs_model():
input_a = keras.layers.Input(shape=(16,), name='input_a')
input_b = keras.layers.Input(shape=(16,), name='input_b')
input_m = keras.layers.Input(shape=(8,), dtype='string', name='input_m')
dense = keras.layers.Dense(8, name='dense_1')
interm_a = dense(input_a)
# Read m
interm_m = keras.layers.Lambda(gen_parsing_ops.string_to_number)(input_m)
interm_s = keras.layers.Lambda(lambda k: k[0] * k[1])([interm_m, interm_a])
interm_b = dense(input_b)
merged = keras.layers.concatenate([interm_s, interm_b], name='merge')
output_c = keras.layers.Dense(3, activation='softmax', name='dense_2')(merged)
output_d = keras.layers.Dense(2, activation='softmax', name='dense_3')(merged)
model = keras.models.Model(
inputs=[input_a, input_b, input_m], outputs=[output_c, output_d])
model.compile(
loss='categorical_crossentropy',
optimizer=gradient_descent.GradientDescentOptimizer(0.001),
metrics={
'dense_2': 'categorical_accuracy',
'dense_3': 'categorical_accuracy'
})
return model
def get_ds_train_input_fn():
np.random.seed(_RANDOM_SEED)
(x_train, y_train), _ = testing_utils.get_test_data(
@@ -94,6 +121,49 @@ def get_ds_test_input_fn():
return dataset
def get_multi_inputs_multi_outputs_data():
(a_train, c_train), (a_test, c_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=3,
random_seed=_RANDOM_SEED)
(b_train, d_train), (b_test, d_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=2,
random_seed=_RANDOM_SEED)
(m_train, _), (m_test, _) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(8,),
num_classes=2,
random_seed=_RANDOM_SEED)
c_train = keras.utils.to_categorical(c_train)
c_test = keras.utils.to_categorical(c_test)
d_train = keras.utils.to_categorical(d_train)
d_test = keras.utils.to_categorical(d_test)
train_data = {
'input_a': a_train,
'input_b': b_train,
'input_m': m_train,
'output_c': c_train,
'output_d': d_train
}
test_data = {
'input_a': a_test,
'input_b': b_test,
'input_m': m_test,
'output_c': c_test,
'output_d': d_test
}
return (train_data, test_data)
def batch_wrapper(dataset, batch_size, distribution):
# TPUs currently require fully defined input shapes, drop_remainder ensures
# the input will have fully defined shapes.
@@ -121,6 +191,8 @@ class TestEstimatorDistributionStrategy(test_util.TensorFlowTestCase):
gfile.MakeDirs(self._base_dir)
self._config = run_config_lib.RunConfig(
tf_random_seed=_RANDOM_SEED, model_dir=self._base_dir)
self._dist = mirrored_strategy.MirroredStrategy(
devices=['/device:GPU:0', '/device:GPU:1'])
def tearDown(self):
writer_cache.FileWriterCache.clear()
@@ -174,6 +246,53 @@ class TestEstimatorDistributionStrategy(test_util.TensorFlowTestCase):
writer_cache.FileWriterCache.clear()
gfile.DeleteRecursively(self._config.model_dir)
def test_multi_inputs_multi_outputs_with_input_fn_as_dict(self):
train_data, test_data = get_multi_inputs_multi_outputs_data()
def train_input_fn():
input_dict = {
'input_a': train_data['input_a'],
'input_b': train_data['input_b'],
'input_m': train_data['input_m'].astype(np.str)
}
output_dict = {
'dense_2': train_data['output_c'],
'dense_3': train_data['output_d']
}
return dataset_ops.Dataset.from_tensor_slices((input_dict,
output_dict)).batch(16)
def eval_input_fn():
input_dict = {
'input_a': test_data['input_a'],
'input_b': test_data['input_b'],
'input_m': test_data['input_m'].astype(np.str)
}
output_dict = {
'dense_2': test_data['output_c'],
'dense_3': test_data['output_d']
}
return dataset_ops.Dataset.from_tensor_slices((input_dict,
output_dict)).batch(16)
self.do_test_multi_inputs_multi_outputs_with_input_fn(
train_input_fn, eval_input_fn)
def do_test_multi_inputs_multi_outputs_with_input_fn(self, train_input_fn,
eval_input_fn):
config = run_config_lib.RunConfig(
tf_random_seed=_RANDOM_SEED,
model_dir=self._base_dir,
train_distribute=self._dist)
with self.cached_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras_lib.model_to_estimator(keras_model=model, config=config)
baseline_eval_results = est_keras.evaluate(
input_fn=eval_input_fn, steps=1)
est_keras.train(input_fn=train_input_fn, steps=_TRAIN_SIZE / 16)
eval_results = est_keras.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(eval_results['loss'], baseline_eval_results['loss'])
def test_keras_optimizer_with_distribution_strategy(self):
dist = mirrored_strategy.MirroredStrategy(
devices=['/device:GPU:0', '/device:GPU:1'])

166
tensorflow/python/estimator/keras_test.py
View File

@@ -102,6 +102,49 @@ def gen_input_fn(x, y=None, batch_size=128, num_epochs=1, shuffle=False):
return input_fn
def get_multi_inputs_multi_outputs_data():
(a_train, c_train), (a_test, c_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=3,
random_seed=_RANDOM_SEED)
(b_train, d_train), (b_test, d_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=2,
random_seed=_RANDOM_SEED)
(m_train, _), (m_test, _) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(8,),
num_classes=2,
random_seed=_RANDOM_SEED)
c_train = keras.utils.to_categorical(c_train)
c_test = keras.utils.to_categorical(c_test)
d_train = keras.utils.to_categorical(d_train)
d_test = keras.utils.to_categorical(d_test)
train_data = {
'input_a': a_train,
'input_b': b_train,
'input_m': m_train,
'output_c': c_train,
'output_d': d_train
}
test_data = {
'input_a': a_test,
'input_b': b_test,
'input_m': m_test,
'output_c': c_test,
'output_d': d_test
}
return (train_data, test_data)
def get_resource_for_simple_model(model_type='sequential',
is_evaluate=False,):
if model_type == 'sequential':
@@ -159,20 +202,21 @@ def randomize_io_type(array, name):
def multi_inputs_multi_outputs_model():
a = keras.layers.Input(shape=(16,), name='input_a')
b = keras.layers.Input(shape=(16,), name='input_b')
m = keras.layers.Input(shape=(8,), dtype='string', name='input_m')
input_a = keras.layers.Input(shape=(16,), name='input_a')
input_b = keras.layers.Input(shape=(16,), name='input_b')
input_m = keras.layers.Input(shape=(8,), dtype='string', name='input_m')
dense = keras.layers.Dense(8, name='dense_1')
a_2 = dense(a)
interm_a = dense(input_a)
# Read m
m_2 = keras.layers.Lambda(gen_parsing_ops.string_to_number)(m)
s_2 = keras.layers.Lambda(lambda k: k[0] * k[1])([m_2, a_2])
b_2 = dense(b)
merged = keras.layers.concatenate([s_2, b_2], name='merge')
c = keras.layers.Dense(3, activation='softmax', name='dense_2')(merged)
d = keras.layers.Dense(2, activation='softmax', name='dense_3')(merged)
model = keras.models.Model(inputs=[a, b, m], outputs=[c, d])
interm_m = keras.layers.Lambda(gen_parsing_ops.string_to_number)(input_m)
interm_s = keras.layers.Lambda(lambda k: k[0] * k[1])([interm_m, interm_a])
interm_b = dense(input_b)
merged = keras.layers.concatenate([interm_s, interm_b], name='merge')
output_c = keras.layers.Dense(3, activation='softmax', name='dense_2')(merged)
output_d = keras.layers.Dense(2, activation='softmax', name='dense_3')(merged)
model = keras.models.Model(
inputs=[input_a, input_b, input_m], outputs=[output_c, output_d])
model.compile(
loss='categorical_crossentropy',
optimizer='rmsprop',
@@ -414,51 +458,85 @@ class TestKerasEstimator(test_util.TensorFlowTestCase):
]
self.assertAllEqual(est_pred, keras_pred)
def test_multi_inputs_multi_outputs(self):
np.random.seed(_RANDOM_SEED)
(a_train, c_train), (a_test, c_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=3)
np.random.seed(_RANDOM_SEED)
(b_train, d_train), (b_test, d_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(16,),
num_classes=2)
np.random.seed(_RANDOM_SEED)
(input_m_train, _), (input_m_test, _) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=(8,),
num_classes=2)
c_train = keras.utils.to_categorical(c_train)
c_test = keras.utils.to_categorical(c_test)
d_train = keras.utils.to_categorical(d_train)
d_test = keras.utils.to_categorical(d_test)
def test_multi_inputs_multi_outputs_with_input_fn_as_dict(self):
train_data, test_data = get_multi_inputs_multi_outputs_data()
def train_input_fn():
input_dict = {'input_a': a_train, 'input_b': b_train,
'input_m': input_m_train.astype(np.str)}
output_dict = {'dense_2': c_train, 'dense_3': d_train}
input_dict = {
'input_a': train_data['input_a'],
'input_b': train_data['input_b'],
'input_m': train_data['input_m'].astype(np.str)
}
output_dict = {
'dense_2': train_data['output_c'],
'dense_3': train_data['output_d']
}
return input_dict, output_dict
def eval_input_fn():
input_dict = {'input_a': a_test, 'input_b': b_test,
'input_m': input_m_test.astype(np.str)}
output_dict = {'dense_2': c_test, 'dense_3': d_test}
input_dict = {
'input_a': test_data['input_a'],
'input_b': test_data['input_b'],
'input_m': test_data['input_m'].astype(np.str)
}
output_dict = {
'dense_2': test_data['output_c'],
'dense_3': test_data['output_d']
}
return input_dict, output_dict
def pred_input_fn():
input_dict = {
'input_a': test_data['input_a'],
'input_b': test_data['input_b'],
'input_m': test_data['input_m'].astype(np.str)
}
return input_dict
self.do_test_multi_inputs_multi_outputs_with_input_fn(
train_input_fn, eval_input_fn, pred_input_fn)
def test_multi_inputs_multi_outputs_with_input_fn_as_list(self):
train_data, test_data = get_multi_inputs_multi_outputs_data()
def train_input_fn():
input_list = [
train_data['input_a'], train_data['input_b'],
train_data['input_m'].astype(np.str)
]
output_list = [train_data['output_c'], train_data['output_d']]
return input_list, output_list
def eval_input_fn():
input_list = [
test_data['input_a'], test_data['input_b'],
test_data['input_m'].astype(np.str)
]
output_list = [test_data['output_c'], test_data['output_d']]
return input_list, output_list
def pred_input_fn():
input_list = [
test_data['input_a'], test_data['input_b'],
test_data['input_m'].astype(np.str)
]
return input_list
self.do_test_multi_inputs_multi_outputs_with_input_fn(
train_input_fn, eval_input_fn, pred_input_fn)
def do_test_multi_inputs_multi_outputs_with_input_fn(
self, train_input_fn, eval_input_fn, pred_input_fn):
with self.cached_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras_lib.model_to_estimator(
keras_model=model, config=self._config)
before_eval_results = est_keras.evaluate(input_fn=eval_input_fn, steps=1)
baseline_eval_results = est_keras.evaluate(
input_fn=eval_input_fn, steps=1)
est_keras.train(input_fn=train_input_fn, steps=_TRAIN_SIZE / 16)
after_eval_results = est_keras.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(after_eval_results['loss'], before_eval_results['loss'])
eval_results = est_keras.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(eval_results['loss'], baseline_eval_results['loss'])
est_keras.predict(input_fn=pred_input_fn)
def test_init_from_file(self):
if h5py is None:

6
tensorflow/python/keras/testing_utils.py
View File

@@ -29,7 +29,8 @@ from tensorflow.python.util import tf_inspect
def get_test_data(train_samples,
test_samples,
input_shape,
num_classes):
num_classes,
random_seed=None):
"""Generates test data to train a model on.
Arguments:
@@ -37,10 +38,13 @@ def get_test_data(train_samples,
test_samples: Integer, how many test samples to generate.
input_shape: Tuple of integers, shape of the inputs.
num_classes: Integer, number of classes for the data and targets.
random_seed: Integer, random seed used by numpy to generate data.
Returns:
A tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
if random_seed is not None:
np.random.seed(random_seed)
num_sample = train_samples + test_samples
templates = 2 * num_classes * np.random.random((num_classes,) + input_shape)
y = np.random.randint(0, num_classes, size=(num_sample,))