Python 神经网络模型

Question

我花了好几个小时来解决这个问题。如果您有任何建议，将不胜感激。

#define model 
    
def nn_model_1():
    model = Sequential()
    model.add(Dense(256, activation='relu'))
    model.add(Dense(128, activation='relu'))
    model.add(Dense(64, activation='relu'))
    model.add(Dense(32, activation='relu'))
    model.add(Dense(1, activation='softmax'))

# Compile model  
    adam = tf.keras.optimizers.Adam(lr=1e-3)
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    
    return model

# Call function here

model_1 = nn_model_1()

# Fit the model and store the history
history_model_1 = model_1.fit(X_train, 
                              y_train,
                              epochs=30,
                              verbose=1,
                              validation_split=0.2,
                              batch_size=128)

我想拟合模型，但它给了我以下错误。我不知道如何解决这个问题。

ValueError: Shapes (None, 10) and (None, 1, 32, 1) are incompatible." 

是否意味着我必须检查有关尺寸的初始编码

Answer 1

您似乎缺少validation_split=0.2 和batch_size=128 之间的逗号，请尝试：

history_model_1 = model_1.fit(X_train, 
                              y_train,
                              epochs=30,
                              verbose=1,
                              validation_split=0.2,
                              batch_size=128)