LSTM 网格搜索

Question

我在下面有一个代码，它实现了一个架构（在网格搜索中），为输入、节点、时期、批量大小和差分时间序列输入生成适当的参数。

我面临的挑战是将神经网络从只有一个 LSTM 隐藏层转换为多个 LSTM 隐藏层。

目前，我只能使用 Dense 类型的隐藏层运行代码，不会抛出任何错误，否则会出现维度错误、元组错误等。

问题仅在神经网络架构部分持续存在。

有效的原始代码：

def model_fit(train, config):
    # unpack config
    n_input, n_nodes, n_epochs, n_batch, n_diff = config

    # Data
    if n_diff > 0:
        train = difference(train, n_diff)

    # Time series to supervised format
    data = series_to_supervised(train, n_in=n_input)

    train_x, train_y = data[:, :-1], data[:, -1]

    # Reshaping input data into [samples, timesteps, features]
    n_features = 1
    train_x = train_x.reshape((train_x.shape[0], train_x.shape[1], n_features))

    # Define model for (Grid search architecture)
    model = Sequential()
    model.add(LSTM(n_nodes, activation='relu', input_shape=(n_input, n_features)))
    model.add(Dense(n_nodes, activation='relu'))
    model.add(Dense(n_nodes, activation='relu'))
    model.add(Dense(n_nodes, activation='relu'))
    model.add(Dense(1))

    # Compile model (Grid search architecture)
    model.compile(loss='mse', optimizer='adam')

    # fit model
    model.fit(train_x, train_y, epochs=n_epochs, batch_size=n_batch, verbose=0)
    return model

修改后的 LSTM 隐藏层代码，运行失败：

# Define model for (Grid search architecture)
model = Sequential() 
model.add(LSTM(n_nodes, activation='relu', input_shape=(n_input, n_features), return_sequences=True))
model.add(LSTM(n_nodes, activation='relu', return_sequences=True))
model.add(LSTM(n_nodes, activation='relu', return_sequences=True))
model.add(LSTM(n_nodes, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(1)))

另一个同样引发错误的变体 - ValueError: Error when checks target: expected time_distributed_4 to have 3 dimensions, but got array with shape (34844, 1)

model = Sequential()
model.add(LSTM(n_nodes, activation='relu', input_shape=(n_input, n_features), return_sequences=True))
model.add(LSTM(n_nodes, activation='relu', return_sequences=False))
model.add(RepeatVector(n_input))
model.add(LSTM(n_nodes, activation='relu', return_sequences=True))
model.add(LSTM(n_nodes, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(n_features)))

有任何建议的人可以帮助我吗？

Answer 1

尝试在最后一层设置return_sequences=False。