cnn代码，使用pytorch，将45x235的低分辨率输入映射为150x675的高分辨率输出,训练数据为700个，测试数据为300个，并且把训练误差和测试误差打印出图片

下面是一个使用PyTorch实现CNN的代码示例，将45x235的低分辨率输入映射为150x675的高分辨率输出。该代码还会打印出训练误差和测试误差的图像。

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.datasets import Dataset
from torchvision.transforms import ToTensor
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt

# 自定义数据集类
class CustomDataset(Dataset):
    def __init__(self, data):
        self.data = data

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]

# 自定义CNN模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=3, stride=1, padding=1)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(32, 1, kernel_size=3, stride=1, padding=1)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.conv3(x)
        return x

# 数据准备
train_data = torch.randn(700, 1, 45, 235)
train_labels = torch.randn(700, 1, 150, 675)
train_dataset = CustomDataset(list(zip(train_data, train_labels)))
train_dataloader = DataLoader(train_dataset, batch_size=32, shuffle=True)

test_data = torch.randn(300, 1, 45, 235)
test_labels = torch.randn(300, 1, 150, 675)
test_dataset = CustomDataset(list(zip(test_data, test_labels)))
test_dataloader = DataLoader(test_dataset, batch_size=32, shuffle=False)

# 模型训练
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CNN().to(device)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train_loss_history = []
test_loss_history = []

for epoch in range(10):
    train_loss = 0.0
    model.train()
    for inputs, labels in train_dataloader:
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()
    train_loss /= len(train_dataloader)
    train_loss_history.append(train_loss)

    test_loss = 0.0
    model.eval()
    with torch.no_grad():
        for inputs, labels in test_dataloader:
            inputs, labels = inputs.to(device), labels.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            test_loss += loss.item()
        test_loss /= len(test_dataloader)
        test_loss_history.append(test_loss)

    print(f"Epoch {epoch+1}: Train Loss: {train_loss:.4f}, Test Loss: {test_loss:.4f}")

# 绘制误差图像
plt.plot(train_loss_history, label='Train Loss')
plt.plot(test_loss_history, label='Test Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()

这段代码定义了一个自定义的数据集类`CustomDataset`，以及一个包含两个卷积层和一个全连接层的CNN模型`CNN`。训练数据和测试数据被分别准备为`train_data`、`train_labels`和`test_data`、`test_labels`。模型使用MSE损失函数进行训练，优化器采用Adam算法。训练过程中，每个epoch的训练误差和测试误差都会被记录下来，并最终以图像的形式显示出来。

你可以根据自己的需求修改代码中的超参数和网络结构。希望这能对你有所帮助！