ValueError: Input 0 of layer "max_pooling2d" is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: (None, 3, 51, 39, 32)

Question

我有两个不同的问题同时出现。

我在使用 MaxPooling2d 时遇到维数问题并且在使用 DQNAgent 时遇到相同的维数问题。

问题是，我可以单独修复它们，但不能同时修复它们。

第一个问题

我正在尝试构建一个多层的 CNN 网络。在我构建模型后，当我尝试运行它时，它给我一个错误。

!pip install PyOpenGL==3.1.* PyOpenGL-accelerate==3.1.*
!pip install tensorflow gym keras-rl2 gym[atari] keras pyvirtualdisplay 

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Convolution2D, MaxPooling2D, Activation
from keras_visualizer import visualizer 
from tensorflow.keras.optimizers import Adam

env = gym.make('Boxing-v0')
height, width, channels = env.observation_space.shape
actions = env.action_space.n

input_shape = (3, 210, 160, 3)   ## input_shape = (batch_size, height, width, channels)

def build_model(height, width, channels, actions):
  model = Sequential()
  model.add(Convolution2D(32, (8,8), strides=(4,4), activation="relu", input_shape=input_shape, data_format="channels_last"))
  model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_last"))
  model.add(Convolution2D(64, (4,4), strides=(1,1), activation="relu"))
  model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_last"))
  model.add(Convolution2D(64, (3,3), activation="relu"))
  model.add(Flatten())
  model.add(Dense(512, activation="relu"))
  model.add(Dense(256, activation="relu"))
  model.add(Dense(actions, activation="linear"))
  return model

model = build_model(height, width, channels, actions)

它给出以下错误：

ValueError: Input 0 of layer "max_pooling2d_12" is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: (None, 3, 51, 39, 32)

第二题

我的 input_shape 是 (3, 210, 160, 3)。我故意使用前 3 个，因为我必须在之前指定 batch_size。如果我之前没有指定它并将它作为 (210, 160, 3) 传递给 build_model 函数，下面的 build_agent 函数会给我另一个错误：

def build_agent(model, actions):
  policy = LinearAnnealedPolicy(EpsGreedyQPolicy(), attr="eps", value_max=1., value_min=.1, value_test=.2, nb_steps=10000)
  memory = SequentialMemory(limit=1000, window_length=3)
  dqn = DQNAgent(model=model, memory=memory, policy=policy,
                 enable_dueling_network=True, dueling_type="avg",
                 nb_actions=actions, nb_steps_warmup=1000)
  return dqn

dqn = build_agent(model, actions)
dqn.compile(Adam(learning_rate=1e-4))

dqn.fit(env, nb_steps=10000, visualize=False, verbose=1)

ValueError: Error when checking input: expected conv2d_11_input to have 4 dimensions, but got array with shape (1, 3, 210, 160, 3)

在模型构建阶段删除批量大小，消除了 MaxPooling2D 不兼容错误，但抛出 DQNAgent 维数错误。将批量大小添加到模型构建阶段可消除 DQNAgent 维度错误，但会引发 MaxPooling2D 不兼容错误。

我真的卡住了

Answer 1

input_shape 有问题。 input_shape=input_shape[1:]

工作示例代码

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Convolution2D, MaxPooling2D, Activation
from tensorflow.keras.optimizers import Adam

input_shape = (3, 210, 160, 3)

model = Sequential()
model.add(Convolution2D(32, (8,8), strides=(4,4), activation="relu", input_shape=input_shape[1:], data_format="channels_last"))
model.add(MaxPooling2D(pool_size=(2,2), data_format="channels_last"))
model.add(Convolution2D(64, (4,4), strides=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_last"))
model.add(Convolution2D(64, (3,3), activation="relu"))
model.add(Flatten())
model.add(Dense(512, activation="relu"))
model.add(Dense(256, activation="relu"))
model.add(Dense(2, activation="linear"))

model.summary()

输出

Model: "sequential_7"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv2d_9 (Conv2D)           (None, 51, 39, 32)        6176      
                                                                 
 max_pooling2d_5 (MaxPooling  (None, 25, 19, 32)       0         
 2D)                                                             
                                                                 
 conv2d_10 (Conv2D)          (None, 22, 16, 64)        32832     
                                                                 
 max_pooling2d_6 (MaxPooling  (None, 11, 8, 64)        0         
 2D)                                                             
                                                                 
 conv2d_11 (Conv2D)          (None, 9, 6, 64)          36928     
                                                                 
 flatten_1 (Flatten)         (None, 3456)              0         
                                                                 
 dense_4 (Dense)             (None, 512)               1769984   
                                                                 
 dense_5 (Dense)             (None, 256)               131328    
                                                                 
 dense_6 (Dense)             (None, 2)                 514       
                                                                 
=================================================================
Total params: 1,977,762
Trainable params: 1,977,762
Non-trainable params: 0

ValueError: Input 0 of layer "max_pooling2d" is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: (None, 3, 51, 39, 32)

ValueError: Input 0 of layer "max_pooling2d" is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: (None, 3, 51, 39, 32)

python

artificial-intelligence

reinforcement-learning

keras

tensorflow