基于预训练的ViT-Base模型，使用包含100种类型水果的数据集进行训练，微调代码

以下是使用PyTorch和torchvision库微调预训练的ViT-Base模型的示例代码：

import torch
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
from torch.optim import lr_scheduler
import torch.nn as nn
import time
import os

# 定义数据集路径和批次大小
data_dir = './fruits-360_dataset/fruits-360'
batch_size = 32

# 定义数据预处理
transform = transforms.Compose(
    [transforms.Resize(256),
     transforms.CenterCrop(224),
     transforms.ToTensor(),
     transforms.Normalize(mean=[0.485, 0.456, 0.406],
                          std=[0.229, 0.224, 0.225])])

# 加载数据集
image_datasets = torchvision.datasets.ImageFolder(os.path.join(data_dir, 'Training'), transform=transform)
dataloaders = torch.utils.data.DataLoader(image_datasets, batch_size=batch_size, shuffle=True, num_workers=4)

# 定义模型
model = torchvision.models.vit_base_patch16_224(pretrained=True)
num_ftrs = model.head.in_features
model.head = nn.Linear(num_ftrs, len(image_datasets.classes))

# 定义优化器
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# 定义学习率调度器
scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

# 定义损失函数
criterion = nn.CrossEntropyLoss()

# 定义设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = model.to(device)

# 训练模型
num_epochs = 10
for epoch in range(num_epochs):
    print('Epoch {}/{}'.format(epoch+1, num_epochs))
    print('-' * 10)

    running_loss = 0.0
    running_corrects = 0

    for inputs, labels in dataloaders:
        inputs = inputs.to(device)
        labels = labels.to(device)

        optimizer.zero_grad()

        with torch.set_grad_enabled(True):
            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)
            loss = criterion(outputs, labels)

            loss.backward()
            optimizer.step()

        running_loss += loss.item() * inputs.size(0)
        running_corrects += torch.sum(preds == labels.data)

    scheduler.step()

    epoch_loss = running_loss / len(image_datasets)
    epoch_acc = running_corrects.double() / len(image_datasets)

    print('Loss: {:.4f} Acc: {:.4f}'.format(epoch_loss, epoch_acc))

其中，我们使用了预训练的ViT-Base模型，并将其头部修改为与数据集分类数相同的线性层。然后，我们定义了优化器、学习率调度器和损失函数，并将模型移动到GPU上进行训练。在训练过程中，我们使用了交叉熵损失函数和随机梯度下降优化器，并使用了学习率调度器来动态调整学习率。最后，我们计算了每个epoch的损失和准确率，并输出结果。