2021-07-10

最新推荐文章于 2025-04-27 13:52:04 发布

雷古小狮子

最新推荐文章于 2025-04-27 13:52:04 发布

阅读量85

点赞数

文章标签：深度学习 cv

原文链接：https://blog.youkuaiyun.com/jacke121/article/details/81456842

版权

该博客介绍了一种使用迁移学习的方法来训练AlexNet模型进行图像分类。首先，定义了数据预处理步骤，包括尺度调整、中心裁剪、随机翻转等。然后，加载训练和测试数据集，并使用DataLoader加载数据。接着，加载预训练的AlexNet模型，冻结其参数，并修改分类层以适应新的任务。最后，设置损失函数、优化器并进行训练，保存和加载模型权重，并测试模型的准确性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

迁移学习

在这里插入代码片# coding=utf-8

# from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
from torchvision import datasets, transforms, models
import matplotlib.pyplot as plt
import os

data_transforms = {
    'train': transforms.Compose([
        transforms.Scale(230),
        transforms.CenterCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
    ]),
    'test': transforms.Compose([
        transforms.Scale(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
    ]),
}

data_directory = './data'
trainset = datasets.ImageFolder(os.path.join(data_directory, 'train'), data_transforms['train'])
testset = datasets.ImageFolder(os.path.join(data_directory, 'test'), data_transforms['test'])

trainloader = torch.utils.data.DataLoader(trainset, batch_size=5, shuffle=True)
testloader = torch.utils.data.DataLoader(testset, batch_size=5, shuffle=True)


def imshow(inputs):
    inputs = inputs / 2 + 0.5
    inputs = inputs.numpy().transpose((1, 2, 0))
    print(inputs)
    plt.imshow(inputs)
    plt.show()


inputs, classes = next(iter(trainloader))

imshow(torchvision.utils.make_grid(inputs))



alexnet = models.alexnet(pretrained=True)

for param in alexnet.parameters():
    param.requires_grad = False

alexnet.classifier = nn.Sequential(
    nn.Dropout(),
    nn.Linear(256 * 6 * 6, 4096),
    nn.ReLU(inplace=True),
    nn.Dropout(),
    nn.Linear(4096, 4096),
    nn.ReLU(inplace=True),
    nn.Linear(4096, 2), )

CUDA = torch.cuda.is_available()

if CUDA:
    alexnet = alexnet.cuda()

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


def train(model, criterion, optimizer, epochs=1):
    for epoch in range(epochs):
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
            if CUDA:
                inputs, labels = inputs.cuda(), labels.cuda()
            optimizer.zero_grad()
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            running_loss += loss.item()
            if i % 10 == 9:
                print('[Epoch:%d, Batch:%5d] Loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
                running_loss = 0.0

    print('Finished Training')


def test(testloader, model):
    correct = 0
    total = 0
    for data in testloader:
        images, labels = data
        if CUDA:
            images = images.cuda()
            labels = labels.cuda()
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum()
    print('Accuracy on the test set: %d %%' % (100 * correct / total))


def load_param(model, path):
    if os.path.exists(path):
        model.load_state_dict(torch.load(path))


def save_param(model, path):
    torch.save(model.state_dict(), path)


load_param(alexnet, 'tl_model.pkl')

train(alexnet, criterion, optimizer, epochs=2)

save_param(alexnet, 'tl_model.pkl')

test(testloader, alexnet)

路径问题：https://blog.youkuaiyun.com/qq_37591637/article/details/103991957
加载数据时出错：https://blog.youkuaiyun.com/jacke121/article/details/81456842
代码：https://blog.youkuaiyun.com/jacke121/article/details/81456842