ValueError: Could not find matching function to call loaded from the SavedModel

Question

我正在尝试加载通过

保存的tf-agents政策

try:
    PolicySaver(collect_policy).save(model_dir + 'collect_policy')
except TypeError:
    tf.saved_model.save(collect_policy, model_dir + 'collect_policy')

try/except块的快速解释：最初创建策略时，我可以通过PolicySaver保存它，但是当我再次加载它进行另一次训练时运行，它是a SavedModel 因此不能被 PolicySaver.

保存

这似乎工作正常，但现在我想使用这个策略进行自我播放，所以我在我的 AIPlayer class 中加载了 self.policy = tf.saved_model.load(policy_path) 的策略。但是，当我尝试使用它进行预测时，它不起作用。这是（测试）代码：

def decide(self, table):
    state = table.getState()
    timestep = ts.restart(np.array([table.getState()], dtype=np.float))
    prediction = self.policy.action(timestep)
    print(prediction)

传递到函数中的 table 包含游戏状态，并且 ts.restart() 函数是从我的自定义 pyEnvironment 中复制的，因此时间步的构造方式与在环境。但是，我收到 prediction=self.policy.action(timestep):

行的以下错误消息

ValueError: Could not find matching function to call loaded from the SavedModel. Got:
  Positional arguments (2 total):
    * TimeStep(step_type=<tf.Tensor 'time_step:0' shape=() dtype=int32>, reward=<tf.Tensor 'time_step_1:0' shape=() dtype=float32>, discount=<tf.Tensor 'time_step_2:0' shape=() dtype=float32>, observation=<tf.Tensor 'time_step_3:0' shape=(1, 79) dtype=float64>)
    * ()
  Keyword arguments: {}

Expected these arguments to match one of the following 2 option(s):

Option 1:
  Positional arguments (2 total):
    * TimeStep(step_type=TensorSpec(shape=(None,), dtype=tf.int32, name='time_step/step_type'), reward=TensorSpec(shape=(None,), dtype=tf.float32, name='time_step/reward'), discount=TensorSpec(shape=(None,), dtype=tf.float32, name='time_step/discount'), observation=TensorSpec(shape=(None,
79), dtype=tf.float64, name='time_step/observation'))
    * ()
  Keyword arguments: {}

Option 2:
  Positional arguments (2 total):
    * TimeStep(step_type=TensorSpec(shape=(None,), dtype=tf.int32, name='step_type'), reward=TensorSpec(shape=(None,), dtype=tf.float32, name='reward'), discount=TensorSpec(shape=(None,), dtype=tf.float32, name='discount'), observation=TensorSpec(shape=(None, 79), dtype=tf.float64, name='observation'))
    * ()
  Keyword arguments: {}

我做错了什么？它真的只是张量名称还是形状问题，我该如何改变它？

如有任何进一步调试的想法，我们将不胜感激。

Answer 1

我通过手动构建 TimeStep 让它工作：

    step_type = tf.convert_to_tensor(
        [0], dtype=tf.int32, name='step_type')
    reward = tf.convert_to_tensor(
        [0], dtype=tf.float32, name='reward')
    discount = tf.convert_to_tensor(
        [1], dtype=tf.float32, name='discount')
    observations = tf.convert_to_tensor(
        [state], dtype=tf.float64, name='observations')
    timestep = ts.TimeStep(step_type, reward, discount, observations)
    prediction = self.policy.action(timestep)

ValueError: Could not find matching function to call loaded from the SavedModel

ValueError: Could not find matching function to call loaded from the SavedModel

python

tensorflow

tensorflow-agents