28b8b9d39f53d8327dbf658048a81b7046ae398f,magpie/nn/models.py,,rnn,#,56

Before Change

     Create and return a keras model of a RNN 
    HIDDEN_LAYER_SIZE = 256

    model = Sequential()

    model.add(GRU(
        HIDDEN_LAYER_SIZE,
        input_dim=embedding_size,
        input_length=SAMPLE_LENGTH,
        init="glorot_uniform",
        inner_init="normal",
        activation="relu",
    ))
    model.add(BatchNormalization())
    model.add(Dropout(0.1))

    model.add(Dense(output_length, activation="sigmoid"))

    model.compile(
        loss="binary_crossentropy",
        optimizer="adam",

After Change

    inputs = Input(shape=(SAMPLE_LENGTH, embedding_size))

    gru = GRU(
        HIDDEN_LAYER_SIZE,
        input_shape=(SAMPLE_LENGTH, embedding_size),
        kernel_initializer="glorot_uniform",
        recurrent_initializer="normal",
        activation="relu",
    )(inputs)

    batch_normalization = BatchNormalization()(gru)
    dropout = Dropout(0.1)(batch_normalization)
    outputs = Dense(output_length, activation="sigmoid")(dropout)

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

    model.compile(

Instances