ValueError：模型输出“Tensor("activation_1/Identity:0", shape=(?, 3), dtype=float32)" 的形状无效

Question

我正在尝试运行以下 github 代码进行股市预测：

https://github.com/multidqn/deep-q-trading

按照他们的说明，我在安装所需的库后运行以下命令：

python main.py 3 0 results_folder

但是，当我运行上述命令时，出现以下错误：

Using TensorFlow backend.
WARNING:tensorflow:From /Users/anisschohra/.local/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:68: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

WARNING:tensorflow:From /Users/anisschohra/.local/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:508: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

WARNING:tensorflow:From /Users/anisschohra/.local/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:3837: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.

Traceback (most recent call last):
  File "main.py", line 92, in <module>
    ensembleFolderName=sys.argv[3]
  File "/Users/anisschohra/deep-q-trading/deepQTrading.py", line 68, in __init__
    enable_double_dqn=True,enable_dueling_network=True)
  File "/Users/anisschohra/.local/lib/python3.7/site-packages/rl/agents/dqn.py", line 107, in __init__
    raise ValueError(f'Model output "{model.output}" has invalid shape. DQN expects a model that has one dimension for each action, in this case {self.nb_actions}.')
ValueError: Model output "Tensor("activation_1/Identity:0", shape=(?, 3), dtype=float32)" has invalid shape. DQN expects a model that has one dimension for each action, in this case 3.

您能帮我解决问题并成功运行代码吗？我一直在寻找错误，但没有找到有效的解决方案。他们的代码（main.py）中的模型架构如下：

model = Sequential()
model.add(Flatten(input_shape=(1,1,68)))
model.add(Dense(35,activation='linear'))
model.add(LeakyReLU(alpha=.001))
model.add(Dense(nb_actions))
model.add(Activation('linear'))

提前致谢。

Answer 1

我和你有同样的问题，我对 RL 不太熟悉，但我想我找到了原因。

if list(model.output.shape) != list((None, self.nb_actions)):
     raise ValueError(f'Model output "{model.output}" has invalid shape. DQN expects a model that has one dimension for each action, in this case {self.nb_actions}.')

根据回溯，这是导致问题的代码。 您的模型的输出形状是张量对象，因此 list(model.output.shape) 将类似于 [Dimension(None), Dimension(3)]，但 list((None, self.nb_actions)) 是 [None, 3]，所以会判断为不同。

所以我认为如果有一种方法可以将模型输出的形状转换为 numpy 或列表对象，我们可以解决这个问题。对不起我的英语不好！