dnn.py 文件源码

def prep_model(inputs, N, s0pad, s1pad, c):
    # Word-level projection before averaging
    inputs[0] = TimeDistributed(Dense(N, activation='relu'))(inputs[0])
    inputs[0] = Lambda(lambda x: K.max(x, axis=1), output_shape=(N, ))(inputs[0])
    inputs[1] = TimeDistributed(Dense(N, activation='relu'))(inputs[1])
    inputs[1] = Lambda(lambda x: K.max(x, axis=1), output_shape=(N, ))(inputs[1])
    merged = concatenate([inputs[0], inputs[1]])

    # Deep
    for i in range(c['deep']):
        merged = Dense(c['nndim'], activation=c['nnact'])(merged)
        merged = Dropout(c['nndropout'])(merged)
        merged = BatchNormalization()(merged)

    is_duplicate = Dense(1, activation='sigmoid')(merged)
    return [is_duplicate], N