將輸入饋入keras順序模型

Question

我正在與Keras進行時間序列預測。 我的輸入數據中有10個時間步長，其形狀為(2688, 10, 1) 2688，10，1 (2688, 10, 1)即train_x.shape和train_y.shape為（2688，10，1）。 嘗試將其輸入模型時出現以下錯誤。

ValueError: Error when checking target: expected activation_1 to have 2 dimensions, but got array with shape (2688, 10, 1)

我提供給第一lstm層的輸入形狀： input_shape=(1, time_steps) **

我可以正確地重塑train_y嗎？

**

    time_steps=10
    train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
    train_y = np.reshape(train_y, (train_y.shape[0], train_y.shape[1], 1))

    # lstm model
    model = Sequential()
    model.add(LSTM(128, input_shape=(time_steps, 1), return_sequences=True))
    model.add(LSTM(64))
    model.add(Dense(1))
    model.add(Activation('linear'))

    model.compile(loss='mse', optimizer='adam')
    history = model.fit(train_x, train_y, epochs=10, validation_data=(test_x, 
    test_y), batch_size=64, verbose=1)

Answer 1

如果您期望形狀（2688、10、1），則不能輸入_shape =（1，time_steps）。 它應該input_shape =（time_steps，1）

Answer 2

train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
train_y = np.reshape(train_y, (train_y.shape[0], train_y.shape[1], 1)

我認為錯誤在這里，您應該給定shape [0]和shape [1]之間的時間步長。

train_x = np.reshape(train_x, (train_x.shape[0], 10,train_x.shape[1]))
train_y = np.reshape(train_y, (train_y.shape[0],10, train_y.shape[1]))

這里的值“ 10”表示時間步長！