编码时出现错误：“AttributeError: 'Sequential' object has no attribute 'predict_classes'”。 这里错了

Question

def classify(file_path):
  global label_packed
  image = Image.open(file_path)
  image = image.resize((30,30))
  image = numpy.expand_dims(image, axis=0)
  image = numpy.array(image)
  pred = model.predict_classes(image)[0]
  sign = classes[pred+1]
  print(sign)
  label.configure(foreground='#011638', text=sign) 

Answer 1

Change the:

model.predict_classes() 

to

model.predict() 

and it'll return a probability. Then you should define a threshold to consider prediction probabilities to one of the classes. Remember that threshold is up to you. You can be strict about that or not. However, I suppose it to be 0.5:

pred_class = np.where(model.predict(example) > 0.5, 1, 0)

Then, you'll get predicted classes.