hier_networks.py 文件源码

def build_hcnn_model(opts, vocab_size=0, maxnum=50, maxlen=50, embedd_dim=50, embedding_weights=None, verbose=False):

    N = maxnum
    L = maxlen

    logger.info("Model parameters: max_sentnum = %d, max_sentlen = %d, embedding dim = %s, nbfilters = %s, filter1_len = %s, filter2_len = %s, drop rate = %s, l2 = %s" % (N, L, embedd_dim,
        opts.nbfilters, opts.filter1_len, opts.filter2_len, opts.dropout, opts.l2_value))

    word_input = Input(shape=(N*L,), dtype='int32', name='word_input')
    x = Embedding(output_dim=embedd_dim, input_dim=vocab_size, input_length=N*L, weights=embedding_weights, name='x')(word_input)
    drop_x = Dropout(opts.dropout, name='drop_x')(x)

    resh_W = Reshape((N, L, embedd_dim), name='resh_W')(drop_x)

    z = TimeDistributed(Convolution1D(opts.nbfilters, opts.filter1_len, border_mode='valid'), name='z')(resh_W)

    avg_z = TimeDistributed(AveragePooling1D(pool_length=L-opts.filter1_len+1), name='avg_z')(z)    # shape= (N, 1, nbfilters)

    resh_z = Reshape((N, opts.nbfilters), name='resh_z')(avg_z)     # shape(N, nbfilters)

    hz = Convolution1D(opts.nbfilters, opts.filter2_len, border_mode='valid', name='hz')(resh_z)
    # avg_h = MeanOverTime(mask_zero=True, name='avg_h')(hz)

    avg_hz = GlobalAveragePooling1D(name='avg_hz')(hz)
    y = Dense(output_dim=1, activation='sigmoid', name='output')(avg_hz)

    model = Model(input=word_input, output=y)

    if verbose:
        model.summary()

    start_time = time.time()
    model.compile(loss='mse', optimizer='rmsprop')
    total_time = time.time() - start_time
    logger.info("Model compiled in %.4f s" % total_time)

    return model