How to plot partial dependence plot with tensorflow

Question

I have gru model, with 5 input variables and 4 output variables.

lstm_model = Sequential()
lstm_model.add(GRU(25, input_shape=(X_train.shape[1],X_train.shape[2]), activation='tanh',recurrent_activation='sigmoid'  ,kernel_initializer='RandomUniform', kernel_regularizer=regularizers.l2(0.01),return_sequences=False))
lstm_model.add(Dense(13,activation='tanh',kernel_initializer='RandomUniform'))
lstm_model.add(Dense(4))
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
lstm_model.compile(loss='mean_squared_error', optimizer='Adam' ,metrics=[metrics.MeanAbsoluteError(name="mean_absolute_error", dtype=None)])

I want to plot PDP for each of the output variables. I am using the following code:

from sklearn.inspection import plot_partial_dependence
disp=plot_partial_dependence(lstm_model, X_train,target=1, verbose =1, features=[0,1,2,3,4],feature_names=f_columns)

This code give error:

NotFittedError: This Sequential instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.