transformers做cifar10图像分类任务保存loss曲线和准确率曲线并保存模型pytorch

好的，您可以按照以下步骤进行：

1. 导入必要的库：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt

2. 定义超参数：

EPOCHS = 20
BATCH_SIZE = 128
LEARNING_RATE = 0.001

3. 加载数据集并进行预处理：

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = DataLoader(testset, batch_size=BATCH_SIZE, shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

4. 定义模型：

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(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()

5. 定义损失函数和优化器：

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=LEARNING_RATE)

6. 训练模型并记录loss和accuracy：

train_losses = []
train_accs = []
test_losses = []
test_accs = []

for epoch in range(EPOCHS):

    # training
    train_loss = 0.0
    train_acc = 0.0
    net.train()
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()
        train_acc += accuracy_score(labels.numpy(), torch.argmax(outputs, axis=1).numpy())

    train_loss /= len(trainloader)
    train_acc /= len(trainloader)
    train_losses.append(train_loss)
    train_accs.append(train_acc)

    # testing
    test_loss = 0.0
    test_acc = 0.0
    net.eval()
    with torch.no_grad():
        for i, data in enumerate(testloader, 0):
            inputs, labels = data
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            test_loss += loss.item()
            test_acc += accuracy_score(labels.numpy(), torch.argmax(outputs, axis=1).numpy())

    test_loss /= len(testloader)
    test_acc /= len(testloader)
    test_losses.append(test_loss)
    test_accs.append(test_acc)

    print('Epoch %d | Train Loss: %.3f | Train Acc: %.3f | Test Loss: %.3f | Test Acc: %.3f' %
          (epoch + 1, train_loss, train_acc, test_loss, test_acc))

7. 画出loss和accuracy曲线：

plt.plot(train_losses, label='Train Loss')
plt.plot(test_losses, label='Test Loss')
plt.legend()
plt.show()

plt.plot(train_accs, label='Train Acc')
plt.plot(test_accs, label='Test Acc')
plt.legend()
plt.show()

8. 保存模型：

PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

这样就完成了对CIFAR-10数据集的图像分类任务，并保存了loss和accuracy曲线以及模型。