conv-neural-network - 在 Pytorch 中构建 CNN 时，元组对象不可调用

Question

我是神经网络的新手，目前正在尝试构建一个具有 2 个卷积层的 CNN。

class CNN(nn.Module):
  def __init__(self):
    super(CNN, self).__init__()
    self.conv1 = nn.Conv2d(in_channels = 1, out_channels = 16, kernel_size = 3, stride = 1, padding = 1), 
    self.maxp1 = nn.MaxPool2d(2),
    self.conv2 = nn.Conv2d(in_channels = 16, out_channels = 16, kernel_size = 3, stride = 1, padding = 1),
    self.fc1 = nn.Linear(16, 64),
    self.fc2 = nn.Linear(64, 10)

  def forward(self, x):
    x = nn.ReLU(self.maxp1(self.conv1(x)))
    x = nn.ReLU(self.maxp2(self.conv1(x)))
    x = x.view(x.size(0), -1)
    x = nn.ReLu(self.fc1(x))
    return self.fc2

我想做的是 ConvLayer- ReLu 激活 - Max Pooling 2x2 - ConvLayer - ReLu 激活 - 展平层 - 完全连接 - ReLu - 完全连接

然而，这让TypeError: 'tuple' object is not callable我x = nn.ReLU(self.maxp1(self.conv1(x)))

我怎样才能解决这个问题？

标签： conv-neural-networkpytorch

Answer 1

您可以更改nn.ReLU为F.relu.

如果你想使用nn.ReLU()，你最好将它声明为__init__方法的一部分，然后在后面调用它forward()：

class CNN(nn.Module):
  def __init__(self):
    super(CNN, self).__init__()
    self.conv1 = nn.Conv2d(in_channels = 1, out_channels = 16, kernel_size = 3, stride = 1, padding = 1), 
    self.maxp1 = nn.MaxPool2d(2),
    self.conv2 = nn.Conv2d(in_channels = 16, out_channels = 16, kernel_size = 3, stride = 1, padding = 1),
    self.fc1 = nn.Linear(16, 64),
    self.fc2 = nn.Linear(64, 10)
    self.relu = nn.ReLU(inplace=True)

  def forward(self, x):
    x = self.relu(self.maxp1(self.conv1(x)))
    x = self.relu(self.maxp2(self.conv1(x)))
    x = x.view(x.size(0), -1)
    x = self.relu(self.fc1(x))
    return self.fc2