pytorch图片分类用alexnet迁移学习

我有4个文件夹，每个文件夹中有不同分辨率但内容相似的PNG图片。请用pytorch引用alexnet做迁移学习写一个图片分类的代码。其中我已经下载了alexnet-owt-7be5be79.pth在本地硬盘了。

这是一个基于迁移学习的图像分类代码，使用了预训练的AlexNet模型。请确保将data_dir变量替换为您的数据目录路径。您可以根据需要调整超参数，例如批量大小、学习率、动量等。如果您需要进一步调整数据预处理步骤，可以修改data_transforms字典。

请注意，这个代码示例没有包括模型的测试和评估。在训练完成后，您可以使用训练好的模型在测试集上进行预测和评估。

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import torchvision
from torchvision import datasets, models, transforms
import os
import numpy as np
import time

# 1. 导入所需的库

# 2. 加载预训练的AlexNet模型
alexnet = models.alexnet(pretrained=False)
alexnet.load_state_dict(torch.load('alexnet-owt-7be5be79.pth'))

# 3. 修改最后一个全连接层以适应类别数量
num_classes = 4
alexnet.classifier[6] = nn.Linear(alexnet.classifier[6].in_features, num_classes)

# 4. 定义数据转换
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 5. 加载图像数据
data_dir = 'path/to/your/data_directory'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4, shuffle=True, num_workers=4) for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

# 6. 定义损失函数、优化器和学习率调度器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(alexnet.parameters(), lr=0.001, momentum=0.9)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

# 7. 训练模型
num_epochs = 25
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
alexnet = alexnet.to(device)

for epoch in range(num_epochs):
    print(f'Epoch {epoch}/{num_epochs - 1}')
    print('-' * 10)

    # Each epoch has a training and validation phase
    for phase in ['train', 'val']:
        if phase == 'train':
            alexnet.train()  # Set model to training mode
        else:
            alexnet.eval()   # Set model to evaluate mode

        running_loss = 0.0
        running_corrects = 0

        # Iterate over data.
        for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)

            # zero the parameter gradients
            optimizer.zero_grad()

            # forward
            with torch.set_grad_enabled(phase == 'train'):
                outputs = alexnet(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)

                # backward + optimize only if in training phase
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

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

        if phase == 'train':
            exp_lr_scheduler.step()

        epoch_loss = running_loss / dataset_sizes[phase]
        epoch_acc = running_corrects.double() / dataset_sizes[phase]

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