打印网络内的层名称与特征图大小

AlexNet 为例子
计算特征图大小的公式，池化与卷积都一样。
全连接的隐藏层数字设置的任意的。

import torch.nn as nn
import torch


class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[48, 55, 55] (224 - 11 + 2*2) / 4 +1 = 217 / 4 +1 = 55
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[48, 27, 27] (55 - 3) / 2 +1  = 52/2 +1 =26 +1
            nn.Conv2d(48, 128, kernel_size=5, padding=2),           # output[128, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 13, 13]
            nn.Conv2d(128, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 128, kernel_size=3, padding=1),          # output[128, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(128 * 6 * 6, 2048),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            nn.Linear(2048, num_classes),
        )
        # if init_weights:
        #     self._initialize_weights()

    def forward(self, x):

        # 运行使用 效率高
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)

        # 调试使用 方便查看 效率低
        # print("输入特征图大小:", x.shape)
        # for i, layer in enumerate(self.features):
        #     x = layer(x)
        #     print(f"第 {i + 1} 个 features 层（{layer.__class__.__name__}）输出特征图大小:", x.shape)
        # x = torch.flatten(x, start_dim=1)
        # print("展平后特征图大小:", x.shape)
        # for i, layer in enumerate(self.classifier):
        #     x = layer(x)
        #     print(f"第 {i + 1} 个 classifier 层（{layer.__class__.__name__}）输出特征图大小:", x.shape)

        return x

    # def _initialize_weights(self):
    #     for m in self.modules():
    #         if isinstance(m, nn.Conv2d):
    #             nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
    #             if m.bias is not None:
    #                 nn.init.constant_(m.bias, 0)
    #         elif isinstance(m, nn.Linear):
    #             nn.init.normal_(m.weight, 0, 0.01)
    #             nn.init.constant_(m.bias, 0)

# 创建 AlexNet 模型实例
model = AlexNet()

# 生成随机输入数组，模拟输入图像数据
# 输入形状为 [batch_size, channels, height, width]
# 这里假设 batch_size 为 1，通道数为 3，图像大小为 224x224
input_tensor = torch.randn(1, 3, 224, 224)

# 进行前向传播
try:
    output = model(input_tensor)
    print("测试通过，网络未报错。")
    print("输出形状:", output.shape)
except Exception as e:
    print("测试失败，网络报错:", e)