How to implement a sequence classification LSTM network in CNTK?

Question

I'm working on implementation of LSTM Neural Network for sequence classification. I want to design a network with the following parameters:

1. Input : a sequence of n one-hot-vectors.
2. Network topology : two-layer LSTM network.
3. Output: a probability that a sequence given belong to a class (binary-classification). I want to take into account only last output from second LSTM layer.

I need to implement that in CNTK but I struggle because its documentation is not written really well. Can someone help me with that?

Answer 1

There is a sequence classification example that follows exactly what you're looking for.

The only difference is that it uses just a single LSTM layer. You can easily change this network to use multiple layers by changing:

LSTM_function = LSTMP_component_with_self_stabilization(
    embedding_function.output, LSTM_dim, cell_dim)[0]

to:

num_layers = 2 # for example
encoder_output = embedding_function.output
for i in range(0, num_layers):
    encoder_output = LSTMP_component_with_self_stabilization(encoder_output.output, LSTM_dim, cell_dim)

However, you'd be better served by using the new layers library. Then you can simply do this:

encoder_output = Stabilizer()(input_sequence)
for i in range(0, num_layers):
    encoder_output = Recurrence(LSTM(hidden_dim)) (encoder_output.output)

Then, to get your final output that you'd put into a dense output layer, you can first do:

final_output = sequence.last(encoder_output)

and then

z = Dense(vocab_dim) (final_output)