def tune_mlp_model():
_, data = load_data.load_cook_train_data(isLemmatize=True)
num_layers = [1, 2, 3]
num_units = [8, 16, 32, 64, 128]
dropout_rates = [0.1, 0.2, 0.3, 0.4]
params = {
# 'layers': [],
# 'units': [],
'dropout_rate': [],
'accuracy': []
}
# for layers in num_layers:
# for units in num_units:
for dropout_rate in dropout_rates:
# params['layers'] = layers
# params['units'] = units
params['dropout_rate'] = dropout_rate
accuracy, _ = train_mlp_model.train_mlp_model(
data,
# units=units,
# layers=layers,
dropout_rate=dropout_rate)
# print('Accuracy: {accuracy}, Parameters: (layers={layers}, '
# 'units={units})'.format(accuracy=accuracy, units=units, layers=layers))
print('Accuracy: {accuracy}, Parameters: dropout_rate={dropout_rate}'.
format(accuracy=accuracy, dropout_rate=dropout_rate))
params['accuracy'] = accuracy
_plot_parameters(params)
if num_classes == 2:
loss = 'binary_crossentropy'
else:
loss = 'sparse_categorical_crossentropy'
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer, loss=loss, metrics=['acc'])
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=2)
]
history = model.fit(x_train,
train_labels,
epochs=epochs,
callbacks=callbacks,
validation_data=(x_val, val_labels),
verbose=2,
batch_size=batch_size)
history = history.history
print('Validation accuracy: {acc}, loss: {loss}'.format(
acc=history['val_acc'][-1], loss=history['val_loss'][-1]))
model.save('rotten_tomatoes_sepcnn_model.h5')
return history['val_acc'][-1], history['val_loss'][-1]
if __name__ == '__main__':
class_names, data = load_data.load_cook_train_data(isLemmatize=True)
print(class_names)
train_sequence_model(data)