Question

我有几个人类活动识别数据的数据文件，这些数据文件由记录的原始样本的按时间顺序排列的行组成。每行有8列EMG传感器数据和1列对应的目标传感器数据。我正在尝试将EMG传感器数据的8个通道输入CNN + LSTM深度模型中，以便预测目标数据的1个通道。为此，我将数据集（下图中的 a ）分解为50行原始样本窗口（下图中的 b ），然后将这些窗口重塑为4个窗口的块，用作模型LSTM部分的时间步长（下图中的 c ）。下图有望更好地解释它：

我一直在遵循有关如何实现模型的教程：https://medium.com/smileinnovation/how-to-work-with-time-distributed-data-in-a-neural-network-b8b39aa4ce00

我已经重塑了数据并构建了模型，但是继续出现以下错误，我无法解决：

    "ValueError: Error when checking target: expected FC_out to have 2 dimensions, but got array with shape (808, 50, 1)"

我的代码如下，并使用Keras和Tensorflow用Python编写：

    from keras.models import Sequential
    from keras.layers import CuDNNLSTM
    from keras.layers.convolutional import Conv2D
    from keras.layers.core import Dense, Dropout
    from keras.layers import Flatten
    from keras.layers import TimeDistributed

    #Code that reads in file data and shapes it into 4-window blocks omitted. That code produces the following arrays:
    #x_train  - shape of (808, 4, 50, 8) which equates to (samples, time steps, window length, number of channels)
    #x_valid  - shape of (223, 4, 50, 8) which equates to the same as x_train
    #y_train  - shape of (808, 50, 1) which equates to (samples, window length, number of target channels)


    # Followed machine learning mastery style for ease of reading
    numSteps = x_train.shape[1]
    windowLength = x_train.shape[2]
    numChannels = x_train.shape[3]
    numOutputs = 1

    # Reshape x data for use with TimeDistributed wrapper, adding extra dimension at the end
    x_train = x_train.reshape(x_train.shape[0], numSteps, windowLength, numChannels, 1)
    x_valid = x_valid.reshape(x_valid.shape[0], numSteps, windowLength, numChannels, 1)


    # Build model
    model = Sequential()
    model.add(TimeDistributed(Conv2D(64, (3,3), activation=activation, name="Conv2D_1"), 
                                     input_shape=(numSteps, windowLength, numChannels, 1)))

    model.add(TimeDistributed(Conv2D(64, (3,3), activation=activation, name="Conv2D_2")))
    model.add(Dropout(0.4, name="CNN_Drop_01"))

    # Flatten for passing to LSTM layer
    model.add(TimeDistributed(Flatten(name="Flatten_1")))

    # LSTM and Dropout
    model.add(CuDNNLSTM(28, return_sequences=True, name="LSTM_01"))
    model.add(Dropout(0.4, name="Drop_01"))

    # Second LSTM and Dropout
    model.add(CuDNNLSTM(28, return_sequences=False, name="LSTM_02"))
    model.add(Dropout(0.3, name="Drop_02"))

    # Fully Connected layer and further Dropout
    model.add(Dense(16, activation=activation, name="FC_1"))
    model.add(Dropout(0.4)) # For example, for 3 outputs classes 

    # Final fully Connected layer specifying outputs
    model.add(Dense(numOutputs, activation=activation, name="FC_out"))

    # Compile model, produce summary and save model image to file
    # NOTE: coeffDetermination refers to a function for calculating R2 and is not included in this code
    model.compile(optimizer='Adam', loss='mse', metrics=[coeffDetermination])


    # Now train the model
    history_cb = model.fit(x_train, y_train, validation_data=(x_valid, y_valid), epochs=30, batch_size=64)

如果有人能弄清楚我做错了什么，我将不胜感激。还是我尝试使用这种模型配置进行时间序列预测而采用了错误的方式？

Answer 1

“ ValueError：检查目标时出错：预期FC_out具有2维，但数组的形状为（808，50，1）”

您的输入为（808，4，50，8，1），输出为（808，50，1）
但是，从model.summary（）中可以看出，输出形状应为（None，4，1）
由于时间步长为4，因此y_train应该类似于（808，4，1）。
或者，如果您想拥有（888，50，1），则需要更改模型以将最后一部分设为（None，50，1）。

Model: "sequential_10"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
time_distributed_18 (TimeDis (None, 4, 48, 6, 64)      640       
_________________________________________________________________
time_distributed_19 (TimeDis (None, 4, 46, 4, 64)      36928     
_________________________________________________________________
CNN_Drop_01 (Dropout)        (None, 4, 46, 4, 64)      0         
_________________________________________________________________
time_distributed_20 (TimeDis (None, 4, 11776)          0         
_________________________________________________________________
LSTM_01 (LSTM)               (None, 4, 28)             1322160   
_________________________________________________________________
Drop_01 (Dropout)            (None, 4, 28)             0         
_________________________________________________________________
Drop_02 (Dropout)            (None, 4, 28)             0         
_________________________________________________________________
FC_1 (Dense)                 (None, 4, 16)             464       
_________________________________________________________________
dropout_3 (Dropout)          (None, 4, 16)             0         
_________________________________________________________________
FC_out (Dense)               (None, 4, 1)              17        
=================================================================
Total params: 1,360,209
Trainable params: 1,360,209
Non-trainable params: 0

对于具有不同序列长度的多对多序列预测，请检查此链接https://github.com/keras-team/keras/issues/6063

dataX or input : (nb_samples, nb_timesteps, nb_features) -> (1000, 50, 1)
dataY or output: (nb_samples, nb_timesteps, nb_features) -> (1000, 10, 1)

model = Sequential()  
model.add(LSTM(input_dim=1, output_dim=hidden_neurons, return_sequences=False))  
model.add(RepeatVector(10))
model.add(LSTM(output_dim=hidden_neurons, return_sequences=True))  
model.add(TimeDistributed(Dense(1)))
model.add(Activation('linear'))   
model.compile(loss='mean_squared_error', optimizer='rmsprop', metrics=['accuracy'])

使用CNN + LSTM模型和TimeDistributed图层包装器进行Keras时间序列预测

1 个答案: