使用CIFAR10数据集实现椒盐噪声的图像去噪

首先，我们需要导入必要的库和数据集：

import torch
import torchvision
import torchvision.transforms as transforms

# 加载CIFAR10数据集
transform = transforms.Compose(
    [transforms.ToTensor()])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)

trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

接下来，我们可以添加一些椒盐噪声到图像中：

import numpy as np

def add_salt_and_pepper(img, noise_ratio=0.05):
    """
    添加椒盐噪声
    """
    img = np.array(img)
    h, w, c = img.shape
    mask = np.random.choice((0, 1, 2), size=(h, w, 1), p=[noise_ratio, noise_ratio, 1-2*noise_ratio])
    mask = np.repeat(mask, c, axis=2)
    img[mask == 0] = 0
    img[mask == 1] = 255
    return img

然后，我们可以使用 PyTorch 中的卷积神经网络（CNN）来实现图像去噪：

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

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        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 = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()

接下来，我们需要定义损失函数和优化器：

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

最后，我们可以训练模型并测试：

for epoch in range(2):  # 进行两轮训练

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # 获取输入
        inputs, labels = data

        # 添加椒盐噪声
        inputs = [add_salt_and_pepper(img) for img in inputs]

        inputs = torch.from_numpy(np.array(inputs)).float()
        labels = torch.from_numpy(np.array(labels)).long()

        # 梯度清零
        optimizer.zero_grad()

        # 正向传播，反向传播，优化
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 打印统计信息
        running_loss += loss.item()
        if i % 2000 == 1999:    # 每2000个小批量数据打印一次
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

# 测试
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data

        # 添加椒盐噪声
        inputs = [add_salt_and_pepper(img) for img in images]

        inputs = torch.from_numpy(np.array(inputs)).float()
        labels = torch.from_numpy(np.array(labels)).long()

        outputs = net(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

这样，我们就可以使用 CIFAR10 数据集实现椒盐噪声的图像去噪了。