def test_layer_tracking(self):
with self.cached_session():
model = _get_model(input_shape=(4, ))
if testing_utils.get_model_type() == 'subclass':
# Subclassed model must be built separately.
model._set_inputs(tensor_spec.TensorSpec((None, 4)))
# Ensure that checkpoints are compatible with another model with the same
# layers, even if the model isn't built until after initialization.
layers = _get_layers(input_shape=None, add_input_layer=False)
model2 = models.Sequential(layers)
# Build model by calling it.
model2.predict_on_batch(np.random.random((10, 4)))
model_path = os.path.join(self.get_temp_dir(), 'model_ckpt')
model.save_weights(model_path)
model2_path = os.path.join(self.get_temp_dir(), 'model2_ckpt')
model2.save_weights(model2_path)
# Check that the checkpoints are compatible with both models.
model.load_weights(model2_path)
self.assertAllClose(self.evaluate(model.weights),
self.evaluate(model2.weights))
model.load_weights(model_path)
model2.load_weights(model_path)
self.assertAllClose(self.evaluate(model.weights),
self.evaluate(model2.weights))
def deep(features_shape, number_of_classes, activation_function='relu'):
model = models.Sequential()
# Input
model.add(
layers.InputLayer(input_shape=features_shape,
name='Inputs',
dtype='float32'))
# Flatten
model.add(layers.Flatten(name='Flatten'))
# Dense block
model.add(
layers.Dense(units=512, activation=activation_function, name='Dense1'))
model.add(
layers.Dense(units=512, activation=activation_function, name='Dense2'))
model.add(
layers.Dense(units=512, activation=activation_function, name='Dense3'))
# Predictions
model.add(
layers.Dense(units=number_of_classes,
activation=activation_function,
name='Prediction'))
# Print network summary
model.summary()
return model
def keras_estimator(model_dir, config, params):
"""Creates a Keras Sequential model with layers.
Mean Squared Error (MSE) is a common loss function used for regression.
A common regression metric is Mean Absolute Error (MAE).
Args:
model_dir: (str) file path where training files will be written.
config: (tf.estimator.RunConfig) Configuration options to save model.
params: (dict)
Returns:
A keras.Model
"""
model = models.Sequential()
model.add(
Dense(64,
activation=tf.nn.relu,
input_shape=(params['num_features'], )))
model.add(Dense(64, activation=tf.nn.relu))
model.add(Dense(1))
# Compile model with learning parameters.
optimizer = tf.train.RMSPropOptimizer(
learning_rate=params['learning_rate'])
model.compile(optimizer=optimizer, loss='mse', metrics=['mae'])
return tf.keras.estimator.model_to_estimator(keras_model=model,
model_dir=model_dir,
config=config)
def train(training_data,
targets,
epochs,
batch_size,
validation_split,
hidden_neurons=5):
# Resize data matrix to have 3 dimensions
training_data = training_data[:, numpy.newaxis, :]
targets = targets.transpose()
training_model = models.Sequential()
training_model.add(layers.LSTM(hidden_neurons, return_sequences=True))
training_model.add(layers.LSTM(hidden_neurons, return_sequences=True))
training_model.add(layers.LSTM(hidden_neurons, return_sequences=True))
training_model.add(layers.LSTM(hidden_neurons, return_sequences=True))
training_model.add(layers.LSTM(hidden_neurons))
training_model.add(layers.Dense(1, activation='sigmoid'))
training_model.compile(loss='binary_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
training_history = training_model.fit(training_data,
targets,
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
return training_model, training_history
