cnn_stacking.py 文件源码

def build_model(cat, hidden_dim):
    graph_in = Input(shape=(sequence_length, embedding_dim))
    convs = []
    for fsz in filter_sizes:
        conv = Convolution1D(nb_filter=num_filters,
                             filter_length=fsz,
                             border_mode='valid',
                             activation='relu',
                             subsample_length=1)(graph_in)
        pool = MaxPooling1D(pool_length=2)(conv)
        flatten = Flatten()(pool)
        convs.append(flatten)

    if len(filter_sizes)>1:
        out = Merge(mode='concat')(convs)
    else:
        out = convs[0]

    graph = Model(input=graph_in, output=out)

    # main sequential model
    model = Sequential()
    if not model_variation=='CNN-static':
        model.add(Embedding(len(vocabulary), embedding_dim, input_length=sequence_length,
                            weights=embedding_weights))
    model.add(Dropout(dropout_prob[0], input_shape=(sequence_length, embedding_dim)))
    model.add(graph)
    model.add(Dense(hidden_dim))
    model.add(Dropout(dropout_prob[1]))
    model.add(Activation('relu'))
    model.add(Dense(cat))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model