def main():
# Load data
X, y = load_data('actuator', use_targets=False)
X_seq, y_seq = data_to_seq(X, y,
t_lag=32, t_future_shift=1, t_future_steps=1, t_sw_step=1)
# Split
train_end = int((45. / 100.) * len(X_seq))
test_end = int((90. / 100.) * len(X_seq))
X_train, y_train = X_seq[:train_end], y_seq[:train_end]
X_test, y_test = X_seq[train_end:test_end], y_seq[train_end:test_end]
X_valid, y_valid = X_seq[test_end:], y_seq[test_end:]
data = {
'train': [X_train, y_train],
'valid': [X_valid, y_valid],
'test': [X_test, y_test],
}
# Re-format targets
for set_name in data:
y = data[set_name][1]
y = y.reshape((-1, 1, np.prod(y.shape[1:])))
data[set_name][1] = [y[:,:,i] for i in range(y.shape[2])]
# Model & training parameters
nb_train_samples = data['train'][0].shape[0]
input_shape = list(data['train'][0].shape[1:])
nb_outputs = len(data['train'][1])
gp_input_shape = (1,)
batch_size = 128
epochs = 1
nn_params = {
'H_dim': 16,
'H_activation': 'tanh',
'dropout': 0.1,
}
gp_params = {
'cov': 'SEiso',
'hyp_lik': -2.0,
'hyp_cov': [[-0.7], [0.0]],
'opt': {},
}
# Retrieve model config
nn_configs = load_NN_configs(filename='lstm.yaml',
input_shape=input_shape,
output_shape=gp_input_shape,
params=nn_params)
gp_configs = load_GP_configs(filename='gp.yaml',
nb_outputs=nb_outputs,
batch_size=batch_size,
nb_train_samples=nb_train_samples,
params=gp_params)
# Construct & compile the model
model = assemble('GP-LSTM', [nn_configs['1H'], gp_configs['GP']])
loss = [gen_gp_loss(gp) for gp in model.output_gp_layers]
model.compile(optimizer=Adam(1e-2), loss=loss)
# Callbacks
callbacks = [EarlyStopping(monitor='val_mse', patience=10)]
# Train the model
history = train(model, data, callbacks=callbacks, gp_n_iter=5,
checkpoint='lstm', checkpoint_monitor='val_mse',
epochs=epochs, batch_size=batch_size, verbose=2)
store_training_loss(history=history, filepath="output/training_loss.csv")
# Finetune the model
model.finetune(*data['train'],
batch_size=batch_size,
gp_n_iter=1,
verbose=0)
# Test the model
X_test, y_test = data['test']
y_preds = model.predict(X_test)
rmse_predict = RMSE(y_test, y_preds)
print('Test predict RMSE:', rmse_predict)
store_predict_points(y_test, y_preds, 'output/test_mtl_prediction.csv')
verbose=0,
save_best_only=True,
save_weights_only=True,
mode='auto',
period=1)
history = model.fit(X_train,
y_train,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
validation_data=(X_valid, y_valid),
callbacks=[earlystop, check_point],
verbose=1)
store_training_loss(history=history,
filepath=output_dir + "/training_loss_epochs_" +
str(EPOCHS) + "_lag" + str(time_step_lag) + ".csv")
# Finetune the model
# model.finetune(X_train, y_train, batch_size=BATCH_SIZE, gp_n_iter=10, verbose=1)
# Test the model
X_test = test_inputs['X']
y1_test = test_inputs['target_load']
y2_test = test_inputs['target_imf7']
y3_test = test_inputs['target_imf8']
y4_test = test_inputs['target_imf9']
y5_test = test_inputs['target_imf10']
y1_preds, y2_preds, y3_preds, y4_preds, y5_preds = model.predict(X_test)
save_weights_only=True,
mode='auto',
period=1)
model.load_weights('output/model_checkpoint/weights-improvement-10.hdf5')
history = model.fit(X_train,
y_train,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
initial_epoch=10,
validation_data=(X_valid, y_valid),
callbacks=[earlystop, check_point],
verbose=1)
store_training_loss(history=history,
filepath="output/training_loss_epochs_" + str(EPOCHS) +
".csv")
# Finetune the model
model.finetune(X_train,
y_train,
batch_size=BATCH_SIZE,
gp_n_iter=10,
verbose=1)
# Test the model
X_test = test_inputs['X']
y1_test = test_inputs['target_load']
y2_test = test_inputs['target_imf1']
y3_test = test_inputs['target_imf2']
