Cross-Validation in LSTM - ValueError: Input 0 of layer sequential_3 is incompatible with the layer

Question

我正在尝试对 LSTM 执行 10 折交叉验证，代码如下：

                    # Initialising the RNN
                    regressor = Sequential()
                    
                    # Adding the first LSTM layer and some Dropout regularisation
                    regressor.add(LSTM(units = 350, return_sequences = True, input_shape = (X_train1.shape[1], len(columns1))))
                    regressor.add(Dropout(0.5))
                    
                    # Adding a second LSTM layer and some Dropout regularisation
                    regressor.add(LSTM(units = 350, return_sequences = True))
                    regressor.add(Dropout(0.5))
                    
                    # Adding a third LSTM layer and some Dropout regularisation
                    regressor.add(LSTM(units = 350, return_sequences = True))
                    regressor.add(Dropout(0.5))
                    
                    # Adding a fourth LSTM layer and some Dropout regularisation
                    regressor.add(LSTM(units = 350))
                    regressor.add(Dropout(0.5))
                    
                    # Adding the output layer
                    regressor.add(Dense(units = 1)) 
                    
                    # Compiling the RNN
                    regressor.compile(optimizer = 'rmsprop', loss = 'mean_squared_error',metrics=['accuracy']) 
                        
                    # RNN TRAINING
                    
                    kfold = KFold(n_splits=10, shuffle=True, random_state=0) 
                    val_accuracies = []
                    test_accuracies = []
                    
                
                    i = 1
                    df_metrics = pd.DataFrame()
                    
                    
                    kfold.split(X_train1, y_train1)
                    
                    #for train_index, test_index in kfold.split(disease_df):
                    for train_index, test_index in kfold.split(X_train1, y_train1):
                        
                    
                        #callback = EarlyStopping(monitor='val_accuracy', patience=10,restore_best_weights=True)
                        # Fitting the RNN to the Training set (RUN/TRAIN the model)
                        history = regressor.fit(X_train1, y_train1, epochs = 100, batch_size = 25, validation_split = 0.1, callbacks=[EarlyStopping('val_accuracy', mode='max',patience=5)])
                        
                        i+=1

想法是基于验证准确性缺乏改进，使用 EarlyStopping 执行 10 折交叉验证。第一次折叠运行完美，但每次应该开始第二次折叠时，我都会收到错误消息：

    ValueError: Input 0 of layer sequential_3 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 68)

关于我的输入的注释：

 X_train1.shape[1] = 1
 len(columns1) = 68

因此，出于某些原因，当第二次折叠开始时，X_train1.shape[1] 似乎等于 None。你曾经发生过这些事情吗？谢谢！

Answer 1

我可以立即看到您打算实施的周期中的一些奇怪的事情。我认为你可以安全地摆脱

kfold.split(X_train1, y_train1)

在 for 循环之前。

那么，您不是在选择分割距离，而是在提供整个数据集 X_train1。这看起来更好：

from sklearn.model_selection import KFold
kf = KFold(n_splits=2)


for train_index, test_index in kf.split(X_train1):
 print("TRAIN:", train_index, "TEST:", test_index)
 X_train, X_test = X_train1[train_index], X_train1[test_index]
 y_train, y_test = y_train1[train_index], y_train1[test_index]

Cross-Validation in LSTM - ValueError: Input 0 of layer sequential_3 is incompatible with the layer

Cross-Validation in LSTM - ValueError: Input 0 of layer sequential_3 is incompatible with the layer

python

lstm

keras

tensorflow