AttributeError：“Model”对象没有属性“targets”

Question

当我运行下面的代码时，我得到了一个错误。

def __init__(self, model, sess, loss_fn=None):
    """
    To generate the White-box Attack Agent.
    :param model: the target model which should have the input tensor, the target tensor and the loss tensor.
    :param sess: the tensorflow session.
    :param loss_fn: None if using original loss of the model.
          
    """
    self.model = model
    self.input_tensor = model.inputs[0]
    self.output_tensor = model.outputs[0]
    self.target_tensor = model.targets[0]
    self._sample_weights = model.sample_weights[0]
    if loss_fn is None:
        self.loss_tensor = model.total_loss
        self.gradient_tensor = K.gradients(self.loss_tensor, self.input_tensor)[0]
    else:
        self.set_loss_function(loss_fn)
    self.sess = sess

错误：

self.target_tensor = model.targets[0]  ,   AttributeError: 'Model' object has no attribute 'targets'

我正在使用Tensorflow 1.14.0，keras 2.2.4-tf和python 3.6.13，我该如何解决这个问题？

谢谢

Answer 1

你的函数正在使用的model参数显然是在谈论一个唯一的类，而这个类不是默认的Keras或Tensorflow的一部分。您需要确保传递给函数的model对象是相应类的实例。或者，您可以通过执行以下操作来对其进行jerry rig：

# whatever code instantiates the `model` would be here
...
...

model.targets = [ "targets of an appropriate structure and type go here" ]

然后，当您将该model对象传递给函数时，它将有一个要访问的targets属性。但最好的做法是首先使用正确的对象。

或者，第三种选择:只注释掉有问题的行，并希望它实际上不会在任何地方使用(如果设置了它，它可能会在某个地方或其他地方使用)。

def __init__(self, model, sess, loss_fn=None):
    """
    To generate the White-box Attack Agent.
    :param model: the target model which should have the input tensor, the target tensor and the loss tensor.
    :param sess: the tensorflow session.
    :param loss_fn: None if using original loss of the model.
          
    """
    self.model = model
    self.input_tensor = model.inputs[0]
    self.output_tensor = model.outputs[0]
    #self.target_tensor = model.targets[0]
    self._sample_weights = model.sample_weights[0]
    if loss_fn is None:
        self.loss_tensor = model.total_loss
        self.gradient_tensor = K.gradients(self.loss_tensor, self.input_tensor)[0]
    else:
        self.set_loss_function(loss_fn)
    self.sess = sess