def test_multi_inputs_multi_outputs(self):
np.random.seed(1337)
(a_train, c_train), (a_test, c_test) = testing_utils.get_test_data(
train_samples=200, test_samples=100, input_shape=(32,), num_classes=3)
(b_train, d_train), (b_test, d_test) = testing_utils.get_test_data(
train_samples=200, test_samples=100, input_shape=(32,), 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 train_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(
np.array(a_train, dtype=np.float32), dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(
np.array(b_train, dtype=np.float32), dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(
np.array(c_train, dtype=np.float32), dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(
np.array(d_train, dtype=np.float32), dtype=dtypes.float32)
}
return input_dict, output_dict
def evaluate_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(
np.array(a_test, dtype=np.float32), dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(
np.array(b_test, dtype=np.float32), dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(
np.array(c_test, dtype=np.float32), dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(
np.array(d_test, dtype=np.float32), dtype=dtypes.float32)
}
return input_dict, output_dict
with self.test_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras.estimator.model_to_estimator(
keras_model=model, model_dir=tempfile.mkdtemp(dir=self._base_dir))
est_keras.train(input_fn=train_input_fn, steps=200 * 10 / 16)
eval_results = est_keras.evaluate(input_fn=evaluate_input_fn, steps=1)
self.assertGreater(eval_results['accuracy_dense_2'], 0.5)
self.assertGreater(eval_results['accuracy_dense_3'], 0.5)
def test_image_classification_declarative(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(8, 8, 3),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(
8, 3,
activation='relu',
input_shape=x_train.shape[1:]))
model.add(keras.layers.BatchNormalization())
model.add(keras.layers.Conv2D(
8, 3,
padding='same',
activation='relu'))
model.add(keras.layers.GlobalMaxPooling2D())
model.add(keras.layers.Dense(y_train.shape[-1], activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_test, y_test),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.85)
def get_resource_for_simple_model(is_sequential, is_evaluate):
model = simple_sequential_model(
) if is_sequential else simple_functional_model()
if is_sequential:
model.build()
input_name = model.input_names[0]
np.random.seed(_RANDOM_SEED)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=_INPUT_SIZE,
num_classes=_NUM_CLASS)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
train_input_fn = numpy_io.numpy_input_fn(
x={input_name: x_train},
y=y_train,
shuffle=False,
num_epochs=None,
batch_size=16)
evaluate_input_fn = numpy_io.numpy_input_fn(
x={input_name: x_test}, y=y_test, num_epochs=1, shuffle=False)
predict_input_fn = numpy_io.numpy_input_fn(
x={input_name: x_test}, num_epochs=1, shuffle=False)
inference_input_fn = evaluate_input_fn if is_evaluate else predict_input_fn
return model, (x_train, y_train), (x_test,
y_test), train_input_fn, inference_input_fn
def test_image_classification_sequential(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), _ = testing_utils.get_test_data(
train_samples=100,
test_samples=0,
input_shape=(12, 12, 3),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(
4, 3,
padding='same',
activation='relu',
input_shape=x_train.shape[1:]))
model.add(keras.layers.Conv2D(
8, 3,
padding='same',
activation='relu'))
model.add(keras.layers.Conv2D(
16, 3,
padding='same',
activation='relu'))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(y_train.shape[-1], activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.8),
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_train, y_train),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.7)
def test_video_classification_functional(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(4, 8, 8, 3),
num_classes=3)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
inputs = keras.layers.Input(shape=x_train.shape[1:])
x = keras.layers.TimeDistributed(
keras.layers.Conv2D(4, 3, activation='relu'))(inputs)
x = keras.layers.BatchNormalization()(x)
x = keras.layers.TimeDistributed(keras.layers.GlobalMaxPooling2D())(x)
x = keras.layers.Conv1D(8, 3, activation='relu')(x)
x = keras.layers.Flatten()(x)
outputs = keras.layers.Dense(y_train.shape[-1], activation='softmax')(x)
model = keras.models.Model(inputs, outputs)
model.compile(loss='categorical_crossentropy',
optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.8),
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_test, y_test),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.70)
def test_temporal_sample_weights(self):
num_classes = 5
weighted_class = 3
train_samples = 1000
test_samples = 1000
input_dim = 5
timesteps = 3
model = keras.models.Sequential()
model.add(
keras.layers.TimeDistributed(
keras.layers.Dense(num_classes),
input_shape=(timesteps, input_dim)))
model.add(keras.layers.Activation('softmax'))
np.random.seed(1337)
(_, y_train), _ = testing_utils.get_test_data(
train_samples=train_samples,
test_samples=test_samples,
input_shape=(input_dim,),
num_classes=num_classes)
int_y_train = y_train.copy()
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
class_weight = dict([(i, 1.) for i in range(num_classes)])
class_weight[weighted_class] = 2.
sample_weight = np.ones((y_train.shape[0]))
sample_weight[int_y_train == weighted_class] = 2.
with self.assertRaises(ValueError):
model.compile(
loss='binary_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001),
sample_weight_mode='temporal')
def test_invalid_ionames_error(self):
(x_train, y_train), (_, _) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=100,
input_shape=(10,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
def invald_input_name_input_fn():
input_dict = {'invalid_input_name': x_train}
return input_dict, y_train
def invald_output_name_input_fn():
input_dict = {'input_1': x_train}
output_dict = {'invalid_output_name': y_train}
return input_dict, output_dict
model = simple_functional_model()
model.compile(
loss='categorical_crossentropy', optimizer='adam', metrics=['acc'])
est_keras = keras.estimator.model_to_estimator(
keras_model=model, config=self._config)
with self.test_session():
with self.assertRaises(ValueError):
est_keras.train(input_fn=invald_input_name_input_fn, steps=100)
with self.assertRaises(ValueError):
est_keras.train(input_fn=invald_output_name_input_fn, steps=100)
def test_vector_classification_shared_model(self):
# Test that functional models that feature internal updates
# and internal losses can be shared.
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(10,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
inputs = keras.layers.Input(x_train.shape[1:])
x = keras.layers.Dense(16,
activation='relu',
kernel_regularizer=keras.regularizers.l2(1e-5),
bias_regularizer=keras.regularizers.l2(1e-5),
input_shape=x_train.shape[1:])(inputs)
x = keras.layers.BatchNormalization()(x)
base_model = keras.models.Model(inputs, x)
x = keras.layers.Input(x_train.shape[1:])
y = base_model(x)
y = keras.layers.Dense(y_train.shape[-1], activation='softmax')(y)
model = keras.models.Model(x, y)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_test, y_test),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.85)
def test_TerminateOnNaN(self):
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
cbks = [keras.callbacks.TerminateOnNaN()]
model = keras.models.Sequential()
initializer = keras.initializers.Constant(value=1e5)
for _ in range(5):
model.add(keras.layers.Dense(2,
input_dim=INPUT_DIM,
activation='relu',
kernel_initializer=initializer))
model.add(keras.layers.Dense(NUM_CLASSES))
model.compile(loss='mean_squared_error',
optimizer='rmsprop')
history = model.fit(x_train, y_train, batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks, epochs=20)
loss = history.history['loss']
assert len(loss) == 1
assert loss[0] == np.inf
def _test_optimizer(optimizer, target=0.75):
np.random.seed(1337)
(x_train, y_train), _ = testing_utils.get_test_data(train_samples=1000,
test_samples=200,
input_shape=(10,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
model = _get_model(x_train.shape[1], 20, y_train.shape[1])
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
assert history.history['acc'][-1] >= target
config = keras.optimizers.serialize(optimizer)
optim = keras.optimizers.deserialize(config)
new_config = keras.optimizers.serialize(optim)
new_config['class_name'] = new_config['class_name'].lower()
assert config == new_config
# Test constraints.
model = keras.models.Sequential()
dense = keras.layers.Dense(10,
input_shape=(x_train.shape[1],),
kernel_constraint=lambda x: 0. * x + 1.,
bias_constraint=lambda x: 0. * x + 2.,
activation='relu')
model.add(dense)
model.add(keras.layers.Dense(y_train.shape[1], activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
model.train_on_batch(x_train[:10], y_train[:10])
kernel, bias = dense.get_weights()
np.testing.assert_allclose(kernel, 1., atol=1e-3)
np.testing.assert_allclose(bias, 2., atol=1e-3)
def test_invalid_loss_or_metrics(self):
num_classes = 5
train_samples = 1000
test_samples = 1000
input_dim = 5
model = keras.models.Sequential()
model.add(keras.layers.Dense(10, input_shape=(input_dim,)))
model.add(keras.layers.Activation('relu'))
model.add(keras.layers.Dense(num_classes))
model.add(keras.layers.Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001))
np.random.seed(1337)
(x_train, y_train), (_, _) = testing_utils.get_test_data(
train_samples=train_samples,
test_samples=test_samples,
input_shape=(input_dim,),
num_classes=num_classes)
with self.assertRaises(ValueError):
model.fit(x_train, np.concatenate([y_train, y_train], axis=-1))
with self.assertRaises(TypeError):
model.compile(loss='categorical_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001),
metrics=set(0))
with self.assertRaises(ValueError):
model.compile(loss=None,
optimizer='rms')
def test_LearningRateScheduler(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
cbks = [keras.callbacks.LearningRateScheduler(lambda x: 1. / (1. + x))]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=0)
assert (float(keras.backend.get_value(model.optimizer.lr)) - 0.2
) < keras.backend.epsilon()
def test_vector_classification_declarative(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(10,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
model = keras.models.Sequential([
keras.layers.Dense(16,
activation='relu',
input_shape=x_train.shape[1:]),
keras.layers.Dropout(0.1),
keras.layers.Dense(y_train.shape[-1], activation='softmax')
])
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_test, y_test),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.85)
def test_sample_weights(self):
num_classes = 5
batch_size = 5
epochs = 5
weighted_class = 3
train_samples = 3000
test_samples = 3000
input_dim = 5
model = keras.models.Sequential()
model.add(keras.layers.Dense(10, input_shape=(input_dim,)))
model.add(keras.layers.Activation('relu'))
model.add(keras.layers.Dense(num_classes))
model.add(keras.layers.Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001))
np.random.seed(43)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=train_samples,
test_samples=test_samples,
input_shape=(input_dim,),
num_classes=num_classes)
int_y_test = y_test.copy()
int_y_train = y_train.copy()
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
test_ids = np.where(int_y_test == np.array(weighted_class))[0]
class_weight = dict([(i, 1.) for i in range(num_classes)])
class_weight[weighted_class] = 2.
sample_weight = np.ones((y_train.shape[0]))
sample_weight[int_y_train == weighted_class] = 2.
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=epochs // 3,
verbose=0,
sample_weight=sample_weight)
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=epochs // 3,
verbose=0,
sample_weight=sample_weight,
validation_split=0.1)
model.train_on_batch(
x_train[:batch_size],
y_train[:batch_size],
sample_weight=sample_weight[:batch_size])
model.test_on_batch(
x_train[:batch_size],
y_train[:batch_size],
sample_weight=sample_weight[:batch_size])
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 train_input_fn():
input_dict = {'input_a': a_train, 'input_b': b_train,
'input_m': input_m_train > 0}
output_dict = {'dense_2': c_train, 'dense_3': d_train}
return input_dict, output_dict
def eval_input_fn():
input_dict = {'input_a': a_test, 'input_b': b_test,
'input_m': input_m_test > 0}
output_dict = {'dense_2': c_test, 'dense_3': d_test}
return input_dict, output_dict
with self.test_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras.estimator.model_to_estimator(
keras_model=model, config=self._config)
before_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'])
def test_stop_training_csv(self):
# Test that using the CSVLogger callback with the TerminateOnNaN callback
# does not result in invalid CSVs.
np.random.seed(1337)
tmpdir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, tmpdir)
with self.test_session():
fp = os.path.join(tmpdir, 'test.csv')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
cbks = [keras.callbacks.TerminateOnNaN(), keras.callbacks.CSVLogger(fp)]
model = keras.models.Sequential()
for _ in range(5):
model.add(keras.layers.Dense(2, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='linear'))
model.compile(loss='mean_squared_error',
optimizer='rmsprop')
def data_generator():
i = 0
max_batch_index = len(x_train) // BATCH_SIZE
tot = 0
while 1:
if tot > 3 * len(x_train):
yield (np.ones([BATCH_SIZE, INPUT_DIM]) * np.nan,
np.ones([BATCH_SIZE, NUM_CLASSES]) * np.nan)
else:
yield (x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
i += 1
tot += 1
i %= max_batch_index
history = model.fit_generator(data_generator(),
len(x_train) // BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=20)
loss = history.history['loss']
assert len(loss) > 1
assert loss[-1] == np.inf or np.isnan(loss[-1])
values = []
with open(fp) as f:
for x in csv.reader(f):
# In windows, due to \r\n line ends we may end up reading empty lines
# after each line. Skip empty lines.
if x:
values.append(x)
assert 'nan' in values[-1], 'The last epoch was not logged.'
def get_data():
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=10,
test_samples=10,
input_shape=(DATA_DIM,),
num_classes=NUM_CLASSES)
y_train = keras.utils.to_categorical(y_train, NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test, NUM_CLASSES)
return (x_train, y_train), (x_test, y_test)
def test_ReduceLROnPlateau(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def make_model():
np.random.seed(1337)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer=keras.optimizers.SGD(lr=0.1),
metrics=['accuracy'])
return model
model = make_model()
# This should reduce the LR after the first epoch (due to high epsilon).
cbks = [
keras.callbacks.ReduceLROnPlateau(
monitor='val_loss',
factor=0.1,
epsilon=10,
patience=1,
cooldown=5)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=0)
self.assertAllClose(
float(keras.backend.get_value(model.optimizer.lr)),
0.01,
atol=1e-4)
def get_resource_for_simple_model(model_type='sequential',
is_evaluate=False,):
if model_type == 'sequential':
model = simple_sequential_model()
model.build()
elif model_type == 'subclass':
model = simple_subclassed_model()
else:
assert model_type == 'functional'
model = simple_functional_model()
if model_type == 'subclass':
input_name = 'input_1'
output_name = 'output_1'
else:
input_name = model.input_names[0]
output_name = model.output_names[0]
np.random.seed(_RANDOM_SEED)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=_TRAIN_SIZE,
test_samples=50,
input_shape=_INPUT_SIZE,
num_classes=_NUM_CLASS)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
train_input_fn = numpy_io.numpy_input_fn(
x=randomize_io_type(x_train, input_name),
y=randomize_io_type(y_train, output_name),
shuffle=False,
num_epochs=None,
batch_size=16)
evaluate_input_fn = numpy_io.numpy_input_fn(
x=randomize_io_type(x_test, input_name),
y=randomize_io_type(y_test, output_name),
num_epochs=1, shuffle=False)
predict_input_fn = numpy_io.numpy_input_fn(
x=randomize_io_type(x_test, input_name), num_epochs=1, shuffle=False)
inference_input_fn = evaluate_input_fn if is_evaluate else predict_input_fn
return model, (x_train, y_train), (x_test,
y_test), train_input_fn, inference_input_fn
def test_LambdaCallback(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
# Start an arbitrary process that should run during model
# training and be terminated after training has completed.
e = threading.Event()
def target():
e.wait()
t = threading.Thread(target=target)
t.start()
cleanup_callback = keras.callbacks.LambdaCallback(
on_train_end=lambda logs: e.set())
cbks = [cleanup_callback]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=0)
t.join()
assert not t.is_alive()
def test_invalid_ionames_error(self):
np.random.seed(1337)
(x_train, y_train), (_, _) = testing_utils.get_test_data(
train_samples=200, test_samples=100, input_shape=(10,), num_classes=2)
y_train = keras.utils.to_categorical(y_train)
def invald_input_name_input_fn():
input_dict = {
'invalid_input_name':
ops.convert_to_tensor(
np.array(x_train, dtype=np.float32), dtype=dtypes.float32),
}
output = ops.convert_to_tensor(
np.array(y_train, dtype=np.float32), dtype=dtypes.float32)
return input_dict, output
def invald_output_name_input_fn():
input_dict = {
'input_1':
ops.convert_to_tensor(
np.array(x_train, dtype=np.float32), dtype=dtypes.float32),
}
output_dict = {
'invalid_output_name':
ops.convert_to_tensor(
np.array(y_train, dtype=np.float32), dtype=dtypes.float32),
}
return input_dict, output_dict
model = simple_functional_model()
model.compile(
loss='categorical_crossentropy', optimizer='adam', metrics=['acc'])
est_keras = keras.estimator.model_to_estimator(
keras_model=model, model_dir=tempfile.mkdtemp(dir=self._base_dir))
with self.test_session():
with self.assertRaises(ValueError):
est_keras.train(input_fn=invald_input_name_input_fn, steps=100)
with self.assertRaises(ValueError):
est_keras.train(input_fn=invald_output_name_input_fn, steps=100)
def test_EarlyStopping(self):
with self.test_session():
np.random.seed(123)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
cases = [
('max', 'val_acc'),
('min', 'val_loss'),
('auto', 'val_acc'),
('auto', 'loss'),
('unknown', 'unknown')
]
for mode, monitor in cases:
patience = 0
cbks = [
keras.callbacks.EarlyStopping(
patience=patience, monitor=monitor, mode=mode)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=0)
def test_temporal_classification_sequential(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), _ = testing_utils.get_test_data(
train_samples=100,
test_samples=0,
input_shape=(4, 10),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(keras.layers.LSTM(5, return_sequences=True,
input_shape=x_train.shape[1:]))
model.add(keras.layers.GRU(y_train.shape[-1], activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=keras.optimizers.Adam(lr=0.1),
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=15, batch_size=16,
validation_data=(x_train, y_train),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.7)
def test_using_tf_layers_in_keras_sequential_model(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), _ = testing_utils.get_test_data(
train_samples=100,
test_samples=0,
input_shape=(10,),
num_classes=2)
model = keras.models.Sequential()
model.add(tf_core_layers.Dense(32, activation=nn.relu, input_shape=(10,)))
model.add(tf_core_layers.Dense(2, activation=nn.softmax))
model.summary()
y_train = keras.utils.to_categorical(y_train)
model.compile(loss='categorical_crossentropy',
optimizer=keras.optimizers.Adam(lr=0.1),
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_train, y_train),
verbose=0)
self.assertGreater(history.history['val_acc'][-1], 0.7)
def get_resource_for_simple_model(is_sequential, is_evaluate):
model = simple_sequential_model(
) if is_sequential else simple_functional_model()
if is_sequential:
model.build()
input_name = model.input_names[0]
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(14, 14, 3),
num_classes=3)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
train_input_fn = numpy_io.numpy_input_fn(
x={input_name: np.array(x_train, dtype=np.float32)},
y=np.array(y_train, dtype=np.float32),
shuffle=False,
num_epochs=None,
batch_size=16)
evaluate_input_fn = numpy_io.numpy_input_fn(
x={input_name: np.array(x_test, dtype=np.float32)},
y=np.array(y_test, dtype=np.float32),
num_epochs=1,
shuffle=False)
predict_input_fn = numpy_io.numpy_input_fn(
x={input_name: np.array(x_test, dtype=np.float32)},
num_epochs=1,
shuffle=False)
inference_input_fn = evaluate_input_fn if is_evaluate else predict_input_fn
return model, (x_train, y_train), (x_test,
y_test), train_input_fn, inference_input_fn
def test_vector_classification_functional(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), _ = testing_utils.get_test_data(
train_samples=100,
test_samples=0,
input_shape=(20,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
inputs = keras.layers.Input(shape=x_train.shape[1:])
x = keras.layers.Dense(16, activation='relu')(inputs)
x = keras.layers.Dropout(0.1)(x)
outputs = keras.layers.Dense(y_train.shape[-1], activation='softmax')(x)
model = keras.models.Model(inputs, outputs)
model.compile(loss='categorical_crossentropy',
optimizer=keras.optimizers.Adam(lr=0.1),
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_train, y_train),
verbose=2)
self.assertGreater(history.history['val_acc'][-1], 0.7)
def test_TensorBoard_with_ReduceLROnPlateau(self):
with self.test_session():
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='binary_crossentropy', optimizer='sgd', metrics=['accuracy'])
cbks = [
keras.callbacks.ReduceLROnPlateau(
monitor='val_loss', factor=0.5, patience=4, verbose=1),
keras.callbacks.TensorBoard(log_dir=temp_dir)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=2,
verbose=0)
assert os.path.exists(temp_dir)
def test_using_tf_layers_in_keras_functional_model(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(10,),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
inputs = tf_base_layers.Input(shape=(10,))
x = tf_core_layers.Dense(32, activation=nn.relu)(inputs)
outputs = tf_core_layers.Dense(2, activation=nn.softmax)(x)
model = keras.models.Model(inputs, outputs)
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=10, batch_size=16,
validation_data=(x_test, y_test),
verbose=0)
self.assertGreater(history.history['val_acc'][-1], 0.85)
def test_multi_inputs_multi_outputs(self):
np.random.seed(1337)
(a_train,
c_train), (a_test,
c_test) = testing_utils.get_test_data(train_samples=200,
test_samples=100,
input_shape=(32, ),
num_classes=3)
(b_train,
d_train), (b_test,
d_test) = testing_utils.get_test_data(train_samples=200,
test_samples=100,
input_shape=(32, ),
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 train_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(np.array(a_train, dtype=np.float32),
dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(np.array(b_train, dtype=np.float32),
dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(np.array(c_train, dtype=np.float32),
dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(np.array(d_train, dtype=np.float32),
dtype=dtypes.float32)
}
return input_dict, output_dict
def evaluate_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(np.array(a_test, dtype=np.float32),
dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(np.array(b_test, dtype=np.float32),
dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(np.array(c_test, dtype=np.float32),
dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(np.array(d_test, dtype=np.float32),
dtype=dtypes.float32)
}
return input_dict, output_dict
with self.test_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras.estimator.model_to_estimator(
keras_model=model,
model_dir=tempfile.mkdtemp(dir=self._base_dir))
est_keras.train(input_fn=train_input_fn, steps=200 * 10 / 16)
eval_results = est_keras.evaluate(input_fn=evaluate_input_fn,
steps=1)
self.assertGreater(eval_results['accuracy_dense_2'], 0.5)
self.assertGreater(eval_results['accuracy_dense_3'], 0.5)
def test_TensorBoard_multi_input_output(self):
np.random.seed(1337)
tmpdir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, tmpdir)
with self.test_session():
filepath = os.path.join(tmpdir, 'logs')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def data_generator(train):
if train:
max_batch_index = len(x_train) // BATCH_SIZE
else:
max_batch_index = len(x_test) // BATCH_SIZE
i = 0
while 1:
if train:
# simulate multi-input/output models
yield ([x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2,
[y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2)
else:
yield ([x_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2,
[y_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2)
i += 1
i %= max_batch_index
inp1 = keras.Input((INPUT_DIM,))
inp2 = keras.Input((INPUT_DIM,))
inp = keras.layers.add([inp1, inp2])
hidden = keras.layers.Dense(2, activation='relu')(inp)
hidden = keras.layers.Dropout(0.1)(hidden)
output1 = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
output2 = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
model = keras.models.Model([inp1, inp2], [output1, output2])
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
# we must generate new callbacks for each test, as they aren't stateless
def callbacks_factory(histogram_freq):
return [keras.callbacks.TensorBoard(log_dir=filepath,
histogram_freq=histogram_freq,
write_images=True, write_grads=True,
batch_size=5)]
# fit without validation data
model.fit([x_train] * 2, [y_train] * 2, batch_size=BATCH_SIZE,
callbacks=callbacks_factory(histogram_freq=0), epochs=3)
# fit with validation data and accuracy
model.fit([x_train] * 2, [y_train] * 2, batch_size=BATCH_SIZE,
validation_data=([x_test] * 2, [y_test] * 2),
callbacks=callbacks_factory(histogram_freq=1), epochs=2)
# fit generator without validation data
model.fit_generator(data_generator(True), len(x_train), epochs=2,
callbacks=callbacks_factory(histogram_freq=0))
# fit generator with validation data and accuracy
model.fit_generator(data_generator(True), len(x_train), epochs=2,
validation_data=([x_test] * 2, [y_test] * 2),
callbacks=callbacks_factory(histogram_freq=1))
assert os.path.isdir(filepath)
def test_TensorBoard_multi_input_output(self):
np.random.seed(1337)
tmpdir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, tmpdir)
with self.test_session():
filepath = os.path.join(tmpdir, 'logs')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def data_generator(train):
if train:
max_batch_index = len(x_train) // BATCH_SIZE
else:
max_batch_index = len(x_test) // BATCH_SIZE
i = 0
while 1:
if train:
# simulate multi-input/output models
yield ([x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2,
[y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2)
else:
yield ([x_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2,
[y_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE]] * 2)
i += 1
i %= max_batch_index
inp1 = keras.Input((INPUT_DIM,))
inp2 = keras.Input((INPUT_DIM,))
inp = keras.layers.add([inp1, inp2])
hidden = keras.layers.Dense(2, activation='relu')(inp)
hidden = keras.layers.Dropout(0.1)(hidden)
output1 = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
output2 = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
model = keras.models.Model([inp1, inp2], [output1, output2])
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
# we must generate new callbacks for each test, as they aren't stateless
def callbacks_factory(histogram_freq):
return [keras.callbacks.TensorBoard(log_dir=filepath,
histogram_freq=histogram_freq,
write_images=True, write_grads=True,
batch_size=5)]
# fit without validation data
model.fit([x_train] * 2, [y_train] * 2, batch_size=BATCH_SIZE,
callbacks=callbacks_factory(histogram_freq=0), epochs=3)
# fit with validation data and accuracy
model.fit([x_train] * 2, [y_train] * 2, batch_size=BATCH_SIZE,
validation_data=([x_test] * 2, [y_test] * 2),
callbacks=callbacks_factory(histogram_freq=1), epochs=2)
# fit generator without validation data
model.fit_generator(data_generator(True), len(x_train), epochs=2,
callbacks=callbacks_factory(histogram_freq=0))
# fit generator with validation data and accuracy
model.fit_generator(data_generator(True), len(x_train), epochs=2,
validation_data=([x_test] * 2, [y_test] * 2),
callbacks=callbacks_factory(histogram_freq=1))
assert os.path.isdir(filepath)
def test_TensorBoard_histogram_freq_must_have_validation_data(self):
np.random.seed(1337)
tmpdir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, tmpdir)
with self.test_session():
filepath = os.path.join(tmpdir, 'logs')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def data_generator(train):
if train:
max_batch_index = len(x_train) // BATCH_SIZE
else:
max_batch_index = len(x_test) // BATCH_SIZE
i = 0
while 1:
if train:
# simulate multi-input/output models
yield (x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
else:
yield (x_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
y_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
i += 1
i %= max_batch_index
inp = keras.Input((INPUT_DIM,))
hidden = keras.layers.Dense(2, activation='relu')(inp)
hidden = keras.layers.Dropout(0.1)(hidden)
output = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
model = keras.models.Model(inputs=inp, outputs=output)
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
# we must generate new callbacks for each test, as they aren't stateless
def callbacks_factory(histogram_freq):
return [keras.callbacks.TensorBoard(
log_dir=filepath,
histogram_freq=histogram_freq,
write_images=True, write_grads=True,
batch_size=5)]
# fit w/o validation data should raise ValueError if histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit(
x_train, y_train, batch_size=BATCH_SIZE, callbacks=cbs, epochs=3)
for cb in cbs:
cb.on_train_end()
# fit generator without validation data should raise ValueError if
# histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit_generator(
data_generator(True), len(x_train), epochs=2, callbacks=cbs)
for cb in cbs:
cb.on_train_end()
# fit generator with validation data generator should raise ValueError if
# histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit_generator(
data_generator(True),
len(x_train),
epochs=2,
validation_data=data_generator(False),
validation_steps=1,
callbacks=cbs)
for cb in cbs:
cb.on_train_end()
# Make sure file writer cache is clear to avoid failures during cleanup.
writer_cache.FileWriterCache.clear()
def test_TensorBoard(self):
np.random.seed(1337)
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def data_generator(train):
if train:
max_batch_index = len(x_train) // BATCH_SIZE
else:
max_batch_index = len(x_test) // BATCH_SIZE
i = 0
while 1:
if train:
yield (x_train[i * BATCH_SIZE:(i + 1) * BATCH_SIZE],
y_train[i * BATCH_SIZE:(i + 1) * BATCH_SIZE])
else:
yield (x_test[i * BATCH_SIZE:(i + 1) * BATCH_SIZE],
y_test[i * BATCH_SIZE:(i + 1) * BATCH_SIZE])
i += 1
i %= max_batch_index
# case: Sequential
with self.test_session():
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
tsb = keras.callbacks.TensorBoard(
log_dir=temp_dir, histogram_freq=1, write_images=True,
write_grads=True, batch_size=5)
cbks = [tsb]
# fit with validation data
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=3,
verbose=0)
# fit with validation data and accuracy
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=2,
verbose=0)
# fit generator with validation data
model.fit_generator(
data_generator(True),
len(x_train),
epochs=2,
validation_data=(x_test, y_test),
callbacks=cbks,
verbose=0)
# fit generator without validation data
model.fit_generator(
data_generator(True),
len(x_train),
epochs=2,
callbacks=cbks,
verbose=0)
# fit generator with validation data and accuracy
model.fit_generator(
data_generator(True),
len(x_train),
epochs=2,
validation_data=(x_test, y_test),
callbacks=cbks,
verbose=0)
# fit generator without validation data and accuracy
model.fit_generator(
data_generator(True), len(x_train), epochs=2, callbacks=cbks)
assert os.path.exists(temp_dir)
def test_class_weights(self):
num_classes = 5
batch_size = 5
weighted_class = 3
train_samples = 300
test_samples = 300
input_dim = 5
model = keras.models.Sequential()
model.add(keras.layers.Dense(10, input_shape=(input_dim,)))
model.add(keras.layers.Activation('relu'))
model.add(keras.layers.Dense(num_classes))
model.add(keras.layers.Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001))
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=train_samples,
test_samples=test_samples,
input_shape=(input_dim,),
num_classes=num_classes)
int_y_test = y_test.copy()
int_y_train = y_train.copy()
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
test_ids = np.where(int_y_test == np.array(weighted_class))[0]
class_weight = dict([(i, 1.) for i in range(num_classes)])
class_weight[weighted_class] = 4.
sample_weight = np.ones((y_train.shape[0]))
sample_weight[int_y_train == weighted_class] = 4.
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=2,
verbose=0,
class_weight=class_weight,
validation_data=(x_train, y_train, sample_weight))
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=2,
verbose=0,
class_weight=class_weight)
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=2,
verbose=0,
class_weight=class_weight,
validation_split=0.1)
model.train_on_batch(
x_train[:batch_size], y_train[:batch_size], class_weight=class_weight)
ref_score = model.evaluate(x_test, y_test, verbose=0)
score = model.evaluate(
x_test[test_ids, :], y_test[test_ids, :], verbose=0)
self.assertLess(score, ref_score)
def test_class_weight_invalid_use_case(self):
num_classes = 5
train_samples = 1000
test_samples = 1000
input_dim = 5
timesteps = 3
model = keras.models.Sequential()
model.add(
keras.layers.TimeDistributed(
keras.layers.Dense(num_classes),
input_shape=(timesteps, input_dim)))
model.add(keras.layers.Activation('softmax'))
model.compile(
loss='binary_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001))
(x_train, y_train), _ = testing_utils.get_test_data(
train_samples=train_samples,
test_samples=test_samples,
input_shape=(input_dim,),
num_classes=num_classes)
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
class_weight = dict([(i, 1.) for i in range(num_classes)])
del class_weight[1]
with self.assertRaises(ValueError):
model.fit(x_train, y_train,
epochs=0, verbose=0, class_weight=class_weight)
with self.assertRaises(ValueError):
model.compile(
loss='binary_crossentropy',
optimizer=RMSPropOptimizer(learning_rate=0.001),
sample_weight_mode=[])
# Build multi-output model
x = keras.Input((3,))
y1 = keras.layers.Dense(4, name='1')(x)
y2 = keras.layers.Dense(4, name='2')(x)
model = keras.models.Model(x, [y1, y2])
model.compile(optimizer=RMSPropOptimizer(learning_rate=0.001), loss='mse')
x_np = np.random.random((10, 3))
y_np = np.random.random((10, 4))
w_np = np.random.random((10,))
# This will work
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight={'1': w_np})
# These will not
with self.assertRaises(ValueError):
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight=[w_np])
with self.assertRaises(TypeError):
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight=w_np)
with self.assertRaises(ValueError):
bad_w_np = np.random.random((11,))
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight={'1': bad_w_np})
with self.assertRaises(ValueError):
bad_w_np = np.random.random((10, 2))
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight={'1': bad_w_np})
with self.assertRaises(ValueError):
bad_w_np = np.random.random((10, 2, 2))
model.fit(x_np, [y_np, y_np], epochs=1, sample_weight={'1': bad_w_np})
def test_ReduceLROnPlateau(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def make_model():
np.random.seed(1337)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer=keras.optimizers.SGD(lr=0.1),
metrics=['accuracy'])
return model
model = make_model()
# This should reduce the LR after the first epoch (due to high epsilon).
cbks = [
keras.callbacks.ReduceLROnPlateau(
monitor='val_loss',
factor=0.1,
min_delta=10,
patience=1,
cooldown=5)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=0)
self.assertAllClose(
float(keras.backend.get_value(model.optimizer.lr)),
0.01,
atol=1e-4)
model = make_model()
cbks = [
keras.callbacks.ReduceLROnPlateau(
monitor='val_loss',
factor=0.1,
min_delta=0,
patience=1,
cooldown=5)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=5,
verbose=2)
self.assertAllClose(
float(keras.backend.get_value(model.optimizer.lr)), 0.1, atol=1e-4)
def test_CSVLogger(self):
with self.test_session():
np.random.seed(1337)
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
filepath = os.path.join(temp_dir, 'log.tsv')
sep = '\t'
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def make_model():
np.random.seed(1337)
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer=keras.optimizers.SGD(lr=0.1),
metrics=['accuracy'])
return model
# case 1, create new file with defined separator
model = make_model()
cbks = [keras.callbacks.CSVLogger(filepath, separator=sep)]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
assert os.path.exists(filepath)
with open(filepath) as csvfile:
dialect = csv.Sniffer().sniff(csvfile.read())
assert dialect.delimiter == sep
del model
del cbks
# case 2, append data to existing file, skip header
model = make_model()
cbks = [keras.callbacks.CSVLogger(filepath, separator=sep, append=True)]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
# case 3, reuse of CSVLogger object
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
with open(filepath) as csvfile:
output = ' '.join(csvfile.readlines())
assert len(re.findall('epoch', output)) == 1
os.remove(filepath)
def test_TensorBoard_histogram_freq_must_have_validation_data(self):
np.random.seed(1337)
tmpdir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, tmpdir)
with self.test_session():
filepath = os.path.join(tmpdir, 'logs')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
def data_generator(train):
if train:
max_batch_index = len(x_train) // BATCH_SIZE
else:
max_batch_index = len(x_test) // BATCH_SIZE
i = 0
while 1:
if train:
# simulate multi-input/output models
yield (x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
else:
yield (x_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
y_test[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
i += 1
i %= max_batch_index
inp = keras.Input((INPUT_DIM,))
hidden = keras.layers.Dense(2, activation='relu')(inp)
hidden = keras.layers.Dropout(0.1)(hidden)
output = keras.layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
model = keras.models.Model(inputs=inp, outputs=output)
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
# we must generate new callbacks for each test, as they aren't stateless
def callbacks_factory(histogram_freq):
return [keras.callbacks.TensorBoard(
log_dir=filepath,
histogram_freq=histogram_freq,
write_images=True, write_grads=True,
batch_size=5)]
# fit w/o validation data should raise ValueError if histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit(x_train, y_train, batch_size=BATCH_SIZE,
callbacks=cbs, epochs=3)
for cb in cbs:
cb.on_train_end()
# fit generator without validation data should raise ValueError if
# histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit_generator(data_generator(True), len(x_train), epochs=2,
callbacks=cbs)
for cb in cbs:
cb.on_train_end()
# fit generator with validation data generator should raise ValueError if
# histogram_freq > 0
cbs = callbacks_factory(histogram_freq=1)
with self.assertRaises(ValueError):
model.fit_generator(data_generator(True), len(x_train), epochs=2,
validation_data=data_generator(False),
validation_steps=1,
callbacks=cbs)
for cb in cbs:
cb.on_train_end()
# Make sure file writer cache is clear to avoid failures during cleanup.
writer_cache.FileWriterCache.clear()
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)
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 train_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(
np.array(a_train, dtype=np.float32), dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(
np.array(b_train, dtype=np.float32), dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(
np.array(c_train, dtype=np.float32), dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(
np.array(d_train, dtype=np.float32), dtype=dtypes.float32)
}
return input_dict, output_dict
def eval_input_fn():
input_dict = {
'input_a':
ops.convert_to_tensor(
np.array(a_test, dtype=np.float32), dtype=dtypes.float32),
'input_b':
ops.convert_to_tensor(
np.array(b_test, dtype=np.float32), dtype=dtypes.float32)
}
output_dict = {
'dense_2':
ops.convert_to_tensor(
np.array(c_test, dtype=np.float32), dtype=dtypes.float32),
'dense_3':
ops.convert_to_tensor(
np.array(d_test, dtype=np.float32), dtype=dtypes.float32)
}
return input_dict, output_dict
with self.test_session():
model = multi_inputs_multi_outputs_model()
est_keras = keras.estimator.model_to_estimator(
keras_model=model, config=self._config)
before_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'])
def test_ModelCheckpoint(self):
if h5py is None:
return # Skip test if models cannot be saved.
with self.test_session():
np.random.seed(1337)
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
filepath = os.path.join(temp_dir, 'checkpoint.h5')
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=TRAIN_SAMPLES,
test_samples=TEST_SAMPLES,
input_shape=(INPUT_DIM,),
num_classes=NUM_CLASSES)
y_test = keras.utils.to_categorical(y_test)
y_train = keras.utils.to_categorical(y_train)
# case 1
monitor = 'val_loss'
save_best_only = False
mode = 'auto'
model = keras.models.Sequential()
model.add(
keras.layers.Dense(
NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
model.compile(
loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode=mode)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
assert os.path.exists(filepath)
os.remove(filepath)
# case 2
mode = 'min'
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode=mode)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
assert os.path.exists(filepath)
os.remove(filepath)
# case 3
mode = 'max'
monitor = 'val_acc'
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode=mode)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
assert os.path.exists(filepath)
os.remove(filepath)
# case 4
save_best_only = True
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode=mode)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
assert os.path.exists(filepath)
os.remove(filepath)
# Case: metric not available.
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor='unknown',
save_best_only=True)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=1,
verbose=0)
# File won't be written.
assert not os.path.exists(filepath)
# case 5
save_best_only = False
period = 2
mode = 'auto'
filepath = os.path.join(temp_dir, 'checkpoint.{epoch:02d}.h5')
cbks = [
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode=mode,
period=period)
]
model.fit(
x_train,
y_train,
batch_size=BATCH_SIZE,
validation_data=(x_test, y_test),
callbacks=cbks,
epochs=4,
verbose=1)
assert os.path.exists(filepath.format(epoch=2))
assert os.path.exists(filepath.format(epoch=4))
os.remove(filepath.format(epoch=2))
os.remove(filepath.format(epoch=4))
assert not os.path.exists(filepath.format(epoch=1))
assert not os.path.exists(filepath.format(epoch=3))
# Invalid use: this will raise a warning but not an Exception.
keras.callbacks.ModelCheckpoint(
filepath,
monitor=monitor,
save_best_only=save_best_only,
mode='unknown')