def create_model(optimizer="adam"):
        model = Sequential()

        #print "Model Definition"
        model.add(ZeroPadding2D((10,13),input_shape=(6,3,3)))
        model.add(Convolution2D(115,8,8))
        #print model.output_shape
        model.add(MaxPooling2D((7,7)))
        #print model.output_shape
        model.add(Flatten())
        #print model.output_shape
        #model.add(Dense(output_dim=12, input_dim=12, init="he_normal",activation='relu'))
        #model.add(Dense(output_dim=200, input_dim=400, init="he_normal",activation='relu'))
        #model.add(Dense(output_dim=100, input_dim=200, init="he_normal",activation='relu'))
        model.add(Dense(output_dim = 32, input_dim=690, init="he_normal",activation='relu'))
        model.add(Dense(output_dim=1, input_dim=32, init="he_normal",activation='tanh'))
        model.add(Dense(output_dim=1,  init="he_normal", activation='linear'))
        #print model.summary()
        model.compile(loss='mean_squared_error', optimizer=optimizer)

        return model
        #reduce_lr=ReduceLROnPlateau(monitor='val_loss', factor=0.01, patience=3, verbose=1, mode='auto', epsilon=0.1, cooldown=0, min_lr=0.000000000000000001)
        #stop  = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=1, mode='auto')

        #log=csv_logger = CSVLogger('training_'+str(i)+'.csv')
        #print "Model Train"

        #hist_current = model.fit(np.array(data_train_input),
        #                    np.array(data_train_output),
        #                    shuffle=False,
        #                    validation_data=(np.array(data_test_input),np.array(data_test_output)),
        #                    validation_split=0.1,
        #                    nb_epoch=150000,
        #                    verbose=1,
        #                    callbacks=[reduce_lr,log,stop])

        #print()
        #print model.summary()
        #print "Model stored"
        #model.save(spectogram_path+"Model"+str(feature)+".h5")
        #model.save_weights(spectogram_path+"Model"+str(feature)+"_weights.h5")
        #del model



## Make it work for other feature ranges
## Add the CNN part and test it
## Try with gabor kernels as suggested by the other paper..

input_train, input_test, output_train, output_test = model(0,train_input_data_interweawed_normalized,output_data_train,test_input_data_interweawed_normalized,output_data_test)

seed = 7
np.random.seed(seed)
print "Regressor"
model = KerasRegressor(build_fn = create_model, nb_epoch = 100)
optimizer = ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam', 'Adamax', 'Nadam']
param_grid = dict(optimizer=optimizer)
grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=10)
print "Grid fit"
grid_result = grid.fit(np.asarray(input_train[:-(len(input_train)/1000)]), np.array(output_train[:-(len(output_train)/1000)]))

# summarize results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
    print("%f (%f) with: %r" % (mean, stdev, param))