tf.keras set_weights ValueError:Weights for model sequential_1 have not yet been created.

ValueError: Weights for model sequential_1 have not yet been created. Weights are created when the Model is first called on inputs or `build()` is called with an `input_shape`.

ValueError: Weights for model sequential_1 have not yet been created. Weights are created when the Model is first called on inputs or build() is called with an input_shape.
它说模型没创建权重，权重是模型首次调用的时候创建的。

报错的是这句：

self.target_model.set_weights(self.model.get_weights())

target_model()因为没调用过，没有初始权重，直接set_weights()其他模型的权重也不行。
所以在set_weights之前给target_model调用一下：

a_1 = np.argmax(self.target_model.predict(state))

就可以运行了