python - 如何在 PyTorch 中指定多个转换层后的展平层输入大小？

Question

这是我的问题，我在 CIFAR10 数据集上做了一个小测试，如何在 PyTorch 中指定展平层输入大小？如下所示，输入大小为 16*5*5，但是我不知道如何计算它，我想通过某个函数获取输入大小。有人可以在这个 Net 类中编写一个简单的函数并解决这个问题？

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3,6,5)  
        self.conv2 = nn.Conv2d(6,16,5)

        # HERE , the input size is 16*5*5, but I don't know how to get it.
        self.fc1 = nn.Linear(16*5*5, 120)
        self.fc2 = nn.Linear(120,84)
        self.fc3 = nn.Linear(84,10)

    def forward(self, x):
        x = F.max_pool2d(F.relu(self.conv1(x)),(2,2))
        x = F.max_pool2d(F.relu(self.conv2(x)),2)
        x = x.view(x.size()[0],-1)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

Answer 1

Pytorch 默认没有 Flatten Layer。您可以创建一个如下所示的类。干杯

class Flatten(nn.Module):
    def forward(self, input):
        return input.view(input.size(0), -1)


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.flatten   = Flatten()  ## describing the layer
        self.conv1 = nn.Conv2d(3,6,5)  
        self.conv2 = nn.Conv2d(6,16,5)

        # HERE , the input size is 16*5*5, but I don't know how to get it.
        self.fc1 = nn.Linear(16*5*5, 120)
        self.fc2 = nn.Linear(120,84)
        self.fc3 = nn.Linear(84,10)

    def forward(self, x):
        x = F.max_pool2d(F.relu(self.conv1(x)),(2,2))
        x = F.max_pool2d(F.relu(self.conv2(x)),2)
        #x = x.view(x.size()[0],-1)
        x = self.flatten(x)   ### using of flatten layer
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x