Keras LSTM致密层多维输入

我正在尝试创建一个keras LSTM来预测时间序列.我的x_train的形状像3000,15,10(示例，时间步长，特征)，y_train的形状像3000,15,1，我正在尝试建立多对多模型(每个序列10个输入特征使1个输出/序列).

I'm trying to create a keras LSTM to predict time series. My x_train is shaped like 3000,15,10 (Examples, Timesteps, Features), y_train like 3000,15,1 and I'm trying to build a many to many model (10 input features per sequence make 1 output / sequence).

我正在使用的代码是这样:

The code I'm using is this:

model = Sequential()

model.add(LSTM(
    10,
    input_shape=(15, 10),
    return_sequences=True))
model.add(Dropout(0.2))

model.add(LSTM(
    100,
    return_sequences=True))
model.add(Dropout(0.2))
model.add(Dense(1, activation='linear'))
model.compile(loss="mse", optimizer="rmsprop")
model.fit(
        X_train, y_train,
        batch_size=512, nb_epoch=1, validation_split=0.05)

但是，在使用时，我无法拟合模型:

However, I can't fit the model when using :

model.add(Dense(1, activation='linear'))
>> Error when checking model target: expected dense_1 to have 2 dimensions, but got array with shape (3000, 15, 1)

或以这种方式格式化时:

or when formatting it this way:

model.add(Dense(1))
model.add(Activation("linear"))
>> Error when checking model target: expected activation_1 to have 2 dimensions, but got array with shape (3000, 15, 1)

我已经尝试在添加密集层之前展平模型(model.add(Flatten()))，但这只是给了我ValueError: Input 0 is incompatible with layer flatten_1: expected ndim >= 3, found ndim=2.这使我感到困惑，因为我认为我的数据实际上是3维的，不是吗?

I already tried flattening the model ( model.add(Flatten()) ) before adding the dense layer but that just gives me ValueError: Input 0 is incompatible with layer flatten_1: expected ndim >= 3, found ndim=2. This confuses me because I think my data actually is 3 dimensional, isn't it?

代码源自 https://github.com/Vict0rSch/deep_learning /tree/master/keras/recurrent