import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import datasets, transforms

# 定义一个简单的卷积神经网络
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 4, kernel_size=3, padding=1)  # 4个输出通道
        self.conv2 = nn.Conv2d(4, 8, kernel_size=3, padding=1)  # 8个输出通道
        self.fc1 = nn.Linear(8 * 7 * 7, 64)
        self.fc2 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))  # 卷积层1 + ReLU激活函数
        x = F.max_pool2d(x, 2)  # 最大池化层，池化核大小为2x2
        x = F.relu(self.conv2(x))  # 卷积层2 + ReLU激活函数
        x = F.max_pool2d(x, 2)  # 最大池化层，池化核大小为2x2
        x = x.view(x.size(0), -1)  # 展平操作，将多维张量展平成一维
        x = F.relu(self.fc1(x))  # 全连接层1 + ReLU激活函数
        x = self.fc2(x)  # 全连接层2，输出10个类别
        return x

# 实例化模型
model = SimpleCNN()

# 打印剪枝前的模型结构
print("Model before pruning:")
print(model)

# 定义数据增强的转换
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),  # 随机水平翻转
    transforms.RandomRotation(10),  # 随机旋转10度以内
    transforms.ToTensor(),  # 转换为张量
    transforms.Normalize((0.1307,), (0.3081,))  # 归一化
])

# 加载数据
train_dataset = datasets.MNIST('./data', train=True, download=True, transform=transform)  # 加载训练数据集
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)  # 创建数据加载器

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数
optimizer = optim.Adam(model.parameters(), lr=0.001)  # Adam优化器

# 训练模型
model.train()  # 将模型设置为训练模式
for epoch in range(1):  # 训练一个epoch
    running_loss = 0.0
    for data, target in train_loader:
        optimizer.zero_grad()  # 清零梯度
        outputs = model(data)  # 前向传播
        loss = criterion(outputs, target)  # 计算损失
        loss.backward()  # 反向传播
        optimizer.step()  # 更新参数
        running_loss += loss.item() * data.size(0)  # 累加损失

    epoch_loss = running_loss / len(train_loader.dataset)  # 计算平均损失
    print(f'Epoch {epoch + 1}, Loss: {epoch_loss:.4f}')

# 通道剪枝
# 获取卷积层的权重
conv1_weights = model.conv1.weight.data.abs().sum(dim=[1, 2, 3])  # 计算每个通道的L1范数

# 按照L1范数对通道进行排序
sorted_channels = torch.argsort(conv1_weights)

# 选择需要删除的通道
num_prune = 2  # 假设我们要删除2个通道
channels_to_prune = sorted_channels[:num_prune]

print("Channels to prune:", channels_to_prune)

# 删除指定通道的权重和偏置
pruned_weights = torch.index_select(model.conv1.weight.data, 0, sorted_channels[num_prune:])  # 获取保留的权重
pruned_bias = torch.index_select(model.conv1.bias.data, 0, sorted_channels[num_prune:])  # 获取保留的偏置

# 创建一个新的卷积层，并将剪枝后的权重和偏置赋值给它
model.conv1 = nn.Conv2d(in_channels=1, out_channels=4 - num_prune, kernel_size=3, padding=1)
model.conv1.weight.data = pruned_weights
model.conv1.bias.data = pruned_bias

# 同时我们还需要调整conv2层的输入通道
# 获取conv2层的权重并调整其输入通道
conv2_weights = model.conv2.weight.data[:, sorted_channels[num_prune:], :, :]  # 调整输入通道的权重

# 创建一个新的卷积层，并将剪枝后的权重赋值给它
model.conv2 = nn.Conv2d(in_channels=4 - num_prune, out_channels=8, kernel_size=3, padding=1)
model.conv2.weight.data = conv2_weights

# 打印剪枝后的模型结构
print("Model after pruning:")
print(model)

# 定义新的优化器
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 重新训练模型
model.train()  # 将模型设置为训练模式
for epoch in range(1):  # 训练一个epoch
    running_loss = 0.0
    for data, target in train_loader:
        optimizer.zero_grad()  # 清零梯度
        outputs = model(data)  # 前向传播
        loss = criterion(outputs, target)  # 计算损失
        loss.backward()  # 反向传播
        optimizer.step()  # 更新参数
        running_loss += loss.item() * data.size(0)  # 累加损失

    epoch_loss = running_loss / len(train_loader.dataset)  # 计算平均损失
    print(f'Epoch {epoch + 1}, Loss: {epoch_loss:.4f}')

# 加载测试数据
test_transform = transforms.Compose([
    transforms.ToTensor(),  # 转换为张量
    transforms.Normalize((0.1307,), (0.3081,))  # 归一化
])
test_dataset = datasets.MNIST('./data', train=False, transform=test_transform)  # 加载测试数据集
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=1000, shuffle=False)  # 创建数据加载器

# 评估模型
model.eval()  # 将模型设置为评估模式
correct = 0
total = 0
with torch.no_grad():  # 关闭梯度计算
    for data, target in test_loader:
        outputs = model(data)  # 前向传播
        _, predicted = torch.max(outputs.data, 1)  # 获取预测结果
        total += target.size(0)  # 总样本数
        correct += (predicted == target).sum().item()  # 正确预测的样本数

print(f'Accuracy: {100 * correct / total}%')  # 打印准确率