def objective(params):
optimize_model = build_lstm_v1.lstm_multi_104(
params, train_data2.shape[2], H_t2.shape[2],
(std_inv / std_inv2)) #Check code here, relu entering
loss_out = NNFunctions.model_optimizer_101(optimize_model, train_data2,
H_t2, val_data2, H_val2, 5)
return {'loss': loss_out, 'status': STATUS_OK}
(std_inv / std_inv2)) #Check code here, relu entering
loss_out = NNFunctions.model_optimizer_101(optimize_model, train_data2,
H_t2, val_data2, H_val2, 5)
return {'loss': loss_out, 'status': STATUS_OK}
trials = Trials()
best2 = fmin(objective, space2, algo=tpe.suggest, trials=trials, max_evals=20)
#Building Stateful Model
lstm_hidden = hyperopt.space_eval(space2, best2)
print lstm_hidden
tsteps2 = std_inv / std_inv2
#Building model
lstm_model = build_lstm_v1.lstm_multi_104(lstm_hidden, train_data2.shape[2],
H_t2.shape[2], tsteps2)
save_model = lstm_model
##callbacks for Early Stopping
callbacks = [EarlyStopping(monitor='val_loss', patience=5)]
#parameters for simulation
attempt_max = 3
epoch_max = 50
min_epoch = 10
#Criterion for early stopping
tau = 5
e_mat = numpy.zeros((epoch_max, attempt_max))
e_temp = numpy.zeros((tau, ))
