TensorFlow，使用`tf.tensor`作为python`BOOL了

Question

 raise errors.OperatorNotAllowedInGraphError(
tensorflow.python.framework.errors_impl.OperatorNotAllowedInGraphError: using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution. Use Eager execution or decorate this function with @tf.function

代码就是这样。

        self.target = tf.compat.v1.placeholder(tf.float32,    shape = [None], name='Qvals')
        self.actions= tf.compat.v1.placeholder(tf.int32,      shape = [None], name='Actions')

        self.model = AlexNetDuel(self.X, cfg.num_actions, cfg.train_fc)

        self.predict = self.model.output
        ind = tf.one_hot(self.actions, cfg.num_actions)
        pred_Q = tf.reduce_sum(tf.multiply(self.model.output, ind), axis=1)
        self.loss = huber_loss(pred_Q, self.target)
        self.train = tf.cond(tf.optimizers.Adam(lr=self.lr, beta1=0.9, beta2=0.99).minimize(self.loss, name="train"))