Multiclass classification using Tkinter

I was writing a piece of code related to the GUI, trying to connect machine learning model with the interface using Tkinter. I have 4 class classification, what should I do with this error! [classes code]

classes = { 
    0:'its a Normal',
    1:'its a Benign', 
    2:'its an InSitu', 
    3:'its an Invasive', } 

[classify code]

def classify(filename)开发者_如何学编程: 
    global label_packed 
    image = Image.open(filename) 
    image = image.resize((128,128))
    image = numpy.expand_dims(image, axis=0) 
    image = numpy.array(image) 
    image = image/255 
    pred = model.predict_classes([image])[0] 
    sign = classes[pred] 
    print(sign) 
    lb6 = tk.Label(page2, bg='white', width=40)
    lb6.place(x=600, y=530) 
    lb6.configure(text=sign)

[error]

pred = model.predict_classes([image])[0] 
AttributeError: 'Functional' object has no attribute 'predict_classes')

I want when I press the predict button, show what class the uploaded image is.