How to implement a deep bidirectional LSTM with Keras?

model.add(Bidirectional(LSTM(64)))

Keras example

You can use keras.layers.wrappers.Bidirectional. Official manual can be referenced here, https://keras.io/layers/wrappers/#bidirectional

Well, I got the answer for the issue posted on the Keras issues. Hope this would be useful to anyone who look for this kind of approach. How to implement deep bidirectional -LSTM

Now designing BiLSTM is easier. A new class Bidirectional is added as per official doc here: https://www.tensorflow.org/api_docs/python/tf/keras/layers/Bidirectional

For training result & full code