RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 4, 8, 8], but got 2-dimensional input of size [1, 4] instead

Question

我正在使用以下代码初始化卷积 DQN：

class ConvDQN(nn.Module):

    def __init__(self, input_dim, output_dim):
        super(ConvDQN, self).__init__()
        self.input_dim = input_dim
        self.output_dim = output_dim
        self.conv = nn.Sequential(
            nn.Conv2d(self.input_dim, 32, kernel_size=8, stride=4),
            nn.ReLU(),
            nn.Conv2d(32, 64, kernel_size=4, stride=2),
            nn.ReLU(),
            nn.Conv2d(64, 64, kernel_size=3, stride=1),
            nn.ReLU()
        )

        self.fc_input_dim = self.feature_size()

        self.fc = nn.Sequential(
            nn.Linear(self.fc_input_dim, 128),
            nn.ReLU(),
            nn.Linear(128, 256),
            nn.ReLU(),
            nn.Linear(256, self.output_dim)
        )

    def forward(self, state):
        features = self.conv(state)
        features = features.view(features.size(0), -1)
        qvals = self.fc(features)
        return qvals

    def feature_size(self):
        return self.conv(autograd.Variable(torch.zeros(1, *self.input_dim))).view(1, -1).size(1)

它给了我错误：

  File "dqn.py", line 86, in __init__
    self.fc_input_dim = self.feature_size()
  File "dqn.py", line 105, in feature_size
    return self.conv(autograd.Variable(torch.zeros(32, *self.input_dim))).view(1, -1).size(1)
  File "C:\Users\ariji\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\ariji\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\container.py", line 92, in forward
    input = module(input)
  File "C:\Users\ariji\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\ariji\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\conv.py", line 320, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 4, 8, 8], but got 2-dimensional input of size [1, 4] instead

所以我得到一个事实，即我传递给卷积网络的输入尺寸不正确。我不明白的是我应该如何将所需的维度添加到我的输入中？或者我应该改变我的卷积网络中的某些东西吗？

Answer 1

你传递了 conv 层 torch.zeros(1, *self.input_dim)，它是 torch.Size([1, 4])，但是你将 conv 层初始化为，

nn.Sequential(
            nn.Conv2d(self.input_dim, 32, kernel_size=8, stride=4),
            nn.ReLU(),
            nn.Conv2d(32, 64, kernel_size=4, stride=2),
            nn.ReLU(),
            nn.Conv2d(64, 64, kernel_size=3, stride=1),
            nn.ReLU()
        )

所以 self.conv 期待那个大小的张量，但你通过了它 torch.Size([1, 4])

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 4, 8, 8], but got 2-dimensional input of size [1, 4] instead

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 4, 8, 8], but got 2-dimensional input of size [1, 4] instead

python

reinforcement-learning

torch

conv-neural-network

pytorch