# The model can generate output predictions for the input samples.
prediction_values = model.predict_classes(X_test)
print("Prediction values shape:", prediction_values.shape)

# accuracy
print(np.mean(results.history["val_acc"]))

# Now we can check the accuracy of our model
print("Evaluating on training set...")
(loss, accuracy) = model.evaluate(X_train, y_train.T)
print("loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))

print("Evaluating on testing set...")
(loss, accuracy) = model.evaluate(X_test, y_test.T)
print("loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))

Prediction values shape: (660, 1)
0.9532257577628801
Evaluating on training set...
1340/1340 [==============================] - 0s 14us/step
loss=0.0031, accuracy: 99.9254%
Evaluating on testing set...
660/660 [==============================] - 0s 18us/step
loss=0.0023, accuracy: 100.0000%