錯誤在神經網絡

#10-Fold split 
seed = 7 
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed) 
np.random.seed(seed) 
cvscores = [] 

    act = 'relu' 
    for train, test in kfold.split(X, Y): 

     model = Sequential() 

     model.add(Dense(43, input_shape=(8,))) 
     model.add(Activation(act)) 

     model.add(Dense(500)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 

     model.add(Dense(1000)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 

     model.add(Dense(1500)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 


     model.add(Dense(2)) 
     model.add(Activation('softmax')) 

     model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 
     hist = model.fit(X[train], Y[train], 
        epochs=500, 
        shuffle=True, 
        batch_size=100, 
        validation_data=(X[test], Y[test]), verbose=2) 
    #model.summary()

的最後一層當我打電話model.fit它報告以下錯誤：錯誤在神經網絡

ValueError: Error when checking target: expected activation_5 to have shape (None, 2) but got array with shape (3869, 1)

我使用keras與TensorFlow後端。如有需要，請要求進一步澄清。

來源

2017-08-14 Suyash Jain

問題解決了也許https://stackoverflow.com/q/45120429/1741542有點幫助。除此之外，主要觀點似乎是「預期activation_5具有*形狀*（無，2），但是得到*具有形狀的數組*（3869，1）」 –

當我們用這條語句

y = to_categorical(Y[:])

來源

2017-08-15 13:51:20

試試這個：

#10-Fold split 
seed = 7 
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed) 
np.random.seed(seed) 
cvscores = [] 

    act = 'relu' 
    for train, test in kfold.split(X, Y): 

     model = Sequential() 

     model.add(Dense(43, input_shape=(8,))) 
     model.add(Activation(act)) 

     model.add(Dense(500)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 

     model.add(Dense(1000)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 

     model.add(Dense(1500)) 
     model.add(Activation(act)) 
    #model.add(Dropout(0.4)) 


     model.add(Dense(1)) 
     model.add(Activation('softmax')) 

     model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 
     hist = model.fit(X[train], Y[train], 
        epochs=500, 
        shuffle=True, 
        batch_size=100, 
        validation_data=(X[test], Y[test]), verbose=2) 
    #model.summary()

來源

2017-08-14 17:00:46 Paddy

錯誤在神經網絡

回答

相關問題