import torch.nn as nn 
import torch
import torch
import torch.nn as nn
import torch.nn.functional as F

class InceptionModule(nn.Module):
    def __init__(self, in_channels, out_1x1, reduce_3x3, out_3x3, reduce_5x5, out_5x5, out_pool_proj):
        super(InceptionModule, self).__init__()

        #分支1：1*1卷积层
        self.branch1 = nn.Sequential(
            nn.Conv2d(in_channels, out_1x1, kernel_size=1),
            nn.ReLU(True),
        )

        #分支2：1*1卷积层 3*3卷积层
        self.branch2 = nn.Sequential(
            nn.Conv2d(in_channels, reduce_3x3, kernel_size=1),
            nn.ReLU(True),
            nn.Conv2d(reduce_3x3, out_3x3, kernel_size=3, padding=1),
            nn.ReLU(True),
        )

        #分支3：1*1卷积层 5*5卷积层
        self.branch3 = nn.Sequential(
            nn.Conv2d(in_channels, reduce_5x5, kernel_size=1),
            nn.ReLU(True),
            nn.Conv2d(reduce_5x5, out_5x5, kernel_size=5, padding=2),
            nn.ReLU(True),
        )

        #分支4：最大池化层 1*1卷积层
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels, out_pool_proj, kernel_size=1),
            nn.ReLU(True),
        )

    #进行concatenate连接，将四个分支合并一起作为输出
    def forward(self, x):
        outputs = [self.branch1(x), self.branch2(x), self.branch3(x), self.branch4(x)]
        return torch.cat(outputs, 1)


class ImprovedAlexNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(ImprovedAlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),#卷积层1
            nn.ReLU(inplace=True),#激活函数
            nn.MaxPool2d(kernel_size=3, stride=2),#最大池化层1
            InceptionModule(64, 32, 48, 64, 8, 16, 16),  # 替代原始的第一个卷积层
            nn.MaxPool2d(kernel_size=3, stride=2),#最大池化层2
            InceptionModule(128, 64, 96, 128, 16, 32, 32),  # 替代原始的第二个卷积层
            nn.MaxPool2d(kernel_size=3, stride=2),#最大池化层3
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),#Dropout层，表示对输入数据进行随机丢弃操作，丢弃概率为0.5，用于防止过拟合
            nn.Linear(256 * 6 * 6, 2048),#全连接层，将输入特征的维度由(256,6,6)转换为2048，用于进行线性变换操作
            nn.ReLU(inplace=True),#激活函数
            nn.Dropout(p=0.5),#Dropout层，作用同上
            nn.Linear(2048, 2048),#全连接层
            nn.ReLU(inplace=True),#激活函数
            nn.Linear(2048, num_classes),#全连接层
        )

    def forward(self, x):
        x = self.features(x)#进行卷积操作
        x = torch.flatten(x, start_dim=1)#展平
        x = self.classifier(x)#输出
        return x