InvalidArgumentError:维度1的切片索引7超出范围。[Op:Straddslice]名称：Straded_切片/

Question

执行以下代码时获取错误：W tensorflow/core/framework/op_kernel.cc:1622]op_REQUIRES在跨步_slice_op处失败。cc:108:无效参数：使用输入dim 1索引超出范围；输入只有1个DIM

 def random_actions(self,cur_state):
        s=[]
        dest=9
        states=self.get_state(cur_state)
        for index, tuple in enumerate(states):
            actions=tuple[0]
            weights=tuple[1]
            s.append(actions)
            actions=list(s) 
        return actions

num_hidden = 2
num_actions =env.random_actions(3)
inputs = layers.Input(shape=(2))
common = layers.Dense(num_hidden, activation="relu")(inputs)
action = layers.Dense(len(num_actions), activation="softmax")(common)
critic = layers.Dense(1)(common)
model = keras.Model(inputs=inputs, outputs=[action, critic])

state = env.reset()
state=list(state)
with tf.GradientTape() as tape:
    for timestep in range(1, max_steps_per_episode):
        state = tf.convert_to_tensor(state,np.float32)
        action_probs, critic_value = model(state)
        critic_value_history.append(critic_value[0, 0])
        action = np.random.choice(num_actions, p=np.squeeze(action_probs[0]))
        action_probs_history.append(tf.math.log(action_probs[0, action]))
        state, next_state,reward, = env.step(action)
        rewards_history.append(reward)
        steps.append(action)

错误：

在处理以下行时：

    action_probs_history.append(tf.math.log(action_probs[0, action]))

InvalidArgumentError: slice index 7 of dimension 1 out of bounds. [Op:StridedSlice] name: strided_slice/ 

2020-11-23 06:09:03.890424: W tensorflow/core/framework/op_kernel.cc:1622] OP_REQUIRES failed at strided_slice_op.cc:108 : Invalid argument: Index out of range using input dim 1; input has only 1 dims

需要建议。

Answer 1

我想你重新定义了“行动”这个名字。您将其用作密集层输出，并在稍后使用与random.choice（）的输出相同的名称。我不知道这是否是错误的原因，但它看起来肯定不正确