Nrthugu

I have a model implemented in Keras, but I need to implement the same model in tensorflow. So, I am looking to implement only the RNN layer of the model and keep the rest the same, that is, the prediction method, fitting the model... are all implemented in keras. Therefore, here is the code:

Keras model:

def emotion_model(max_seq_len, num_features, learning_rate, num_units_1, num_units_2, bidirectional, dropout, num_targets):

    # Input layer

    inputs = Input(shape=(max_seq_len, num_features))



    # 1st layer

    net = LSTM(num_units_1, return_sequences=True, dropout=dropout, recurrent_dropout=dropout)(net)



    # 2nd layer

    net = LSTM(num_units_2, return_sequences=True, dropout=dropout, recurrent_dropout=dropout)(net)



    # Output layer

    outputs = 

    out1 = TimeDistributed(Dense(1))(net)  # linear activation

    outputs.append(out1)

    if num_targets >= 2:

        out2 = TimeDistributed(Dense(1))(net)  # linear activation

        outputs.append(out2)

    if num_targets == 3:

        out3 = TimeDistributed(Dense(1))(net)  # linear activation

        outputs.append(out3)



    # Create and compile model

    rmsprop = RMSprop(lr=learning_rate)

    model   = Model(inputs=inputs, outputs=outputs)

    model.compile(optimizer=rmsprop, loss=ccc_loss)  # CCC-based loss function

    return model

Now, I would like to replace the LSTM layers above with the equivalent code in tensorflow. Therefore, in a different Module I have implemented the following:

def baseline_model(inputs, cell_Size1, cell_Size2, dropout):

    with tf.variable_scope('model', reuse=tf.AUTO_REUSE):

        cell1 = tf.nn.rnn_cell.LSTMCell(cell_Size1)

        cell1 = tf.nn.rnn_cell.DropoutWrapper(cell1, input_keep_prob=1.0 - dropout, state_keep_prob=1.0 - dropout)



        cell2 = tf.nn.rnn_cell.LSTMCell(cell_Size2)

        cell2 = tf.nn.rnn_cell.DropoutWrapper(cell2, input_keep_prob=1.0 - dropout, state_keep_prob=1.0 - dropout)



        cell = tf.nn.rnn_cell.MultiRNNCell([cell1, cell2], state_is_tuple=True)



        # output1: shape=[1, time_steps, 32]

        output, new_state = tf.nn.dynamic_rnn(cell, inputs, dtype=tf.float32)



        return output

I have tried net = Lambda(partial(baseline_model, dropout))(net) where I removed the cell_size1 and cell_size2 from the method "baseline_model" arguments, yet didn't work

Second, I have tried dumping directly the LSTM layers implemented in tensorflow instead of the LSTM layers in keras above, and this doesn't solve my problem.

Any help is much appreciated!!