VSB Power Line Blog - DNN implementation

model_lstm.py

def model_lstm(input_shape, feat_shape):
  """
  Builds the Neural Network Architecture.

  Following is the architecture that is built:
  * Layer 1
      * LSTM
        * Bidirectional LSTM - 128 neurons
        * Bidirectional LSTM - 64 neurons
      * Attention layer
  * Layer 2
      * Dense - 64, activation: relu
  * Layer 3
    * Output: Dense - 1, activation: sigmoid
  * Loss - binary cross-entropy
  * Optimizer - adam
  * Metric - matthews correlation coefficient
  """
  inp = Input(shape=(input_shape[1], input_shape[2],))
  feat = Input(shape=(feat_shape[1],))

  bi_lstm_1 = Bidirectional(LSTM(128, return_sequences=True), merge_mode='concat')(inp)
  bi_lstm_2 = Bidirectional(GRU(64, return_sequences=True), merge_mode='concat')(bi_lstm_1)

  attention = Attention()(bi_lstm_2)

  x = concatenate([attention, feat], axis=1)
  x = Dense(64, activation='relu')(x)
  x = Dense(1, activation='sigmoid')(x)

  model = Model(inputs=[inp, feat], outputs=x)
  model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[matthews_correlation])

  return model