classifier = []
        classifier.append(nn.Linear(64, 512)) # in_cha
        classifier.append(nn.Linear(512, 2))
        self.classifier = nn.Sequential(*classifier)

import torch
from torch import nn
class Net(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        # 这种情况下,使用数组来构建层毫无意义
        layers = []
        layers.append(nn.Conv2d(3, 32, 3, padding=1))
        layers.append(nn.AdaptiveAvgPool2d(1))
        layers.append(nn.Flatten())
        layers.append(nn.Linear(32, 2))
        self.classifier = nn.Sequential(*layers)
    def forward(self, x):
        return self.classifier(x)
if __name__ == '__main__':
    x = torch.rand(size=(1, 3, 224, 224))
    net = Net()
    print(net(x).shape)

import torch
from torch import nn
class Net(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.classifier = nn.Sequential(
            nn.Conv2d(3, 32, 3, padding=1),
            nn.AdaptiveAvgPool2d(1),
            nn.Flatten(),
            nn.Linear(32, 2)
        )
    def forward(self, x):
        return self.classifier(x)
if __name__ == '__main__':
    x = torch.rand(size=(1, 3, 224, 224))
    net = Net()
    print(net(x).shape)

import torch
from torch import nn
class Net(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        in_channels = 3
        grow = 5
        layers = []
        for i in range(10):
            # 每次增加grow个通道,并保持特征图大小不改变
            layers.append(nn.Conv2d(in_channels, in_channels+grow, 3, padding=1))
            in_channels += grow
        self.block = nn.Sequential(*layers)
        self.classifier = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Flatten(),
            nn.Linear(in_channels, 2)
        )
    def forward(self, x):
        x = self.block(x)
        return self.classifier(x)
if __name__ == '__main__':
    from torchsummary import summary
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    x = torch.rand(size=(1, 3, 224, 224)).to(device)
    net = Net().to(device)
    print(net(x).shape)
    summary(net, (3, 224, 224))