Datawhale：动手深度学习第三次打卡！

最新推荐文章于 2025-07-15 23:56:00 发布

原创最新推荐文章于 2025-07-15 23:56:00 发布 · 328 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

收录于

感悟

本次分享介绍了使用Datawhale动手深度学习项目，通过配合李沐老师的视频教程，深入理解深度学习概念。项目中采用预训练的ResNet18模型进行fine-tuning，针对热狗图片分类任务，展示了从数据预处理到模型训练的全过程。

Datawhale：动手深度学习第三次打卡！

到了最后一次打卡，这次写的代码较少，而是把对应课程的内容看完了，并把后面对应的题做了。

推荐Datawhale的动手深度学习项目，配合着李沐老师的视频更容易理解

import torch
from torch import nn, optim
from torch.utils.data import Dataset, DataLoader
import torchvision
from torchvision.datasets import ImageFolder
from torchvision import transforms
from torchvision import models
import os

import sys

sys.path.append("/home/kesci/input/")
import d2lzh1981 as d2l

os.environ["CUDA_VISIBLE_DEVICES"] = "0"
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

import os
os.listdir('/home/kesci/input/resnet185352')
train_imgs = ImageFolder(os.path.join(data_dir, 'hotdog/train'))
test_imgs = ImageFolder(os.path.join(data_dir, 'hotdog/test'))

hotdogs = [train_imgs[i][0] for i in range(8)]
not_hotdogs = [train_imgs[-i - 1][0] for i in range(8)]
d2l.show_images(hotdogs + not_hotdogs, 2, 8, scale=1.4)

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
train_augs = transforms.Compose([
        transforms.RandomResizedCrop(size=224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        normalize
    ])

test_augs = transforms.Compose([
        transforms.Resize(size=256),
        transforms.CenterCrop(size=224),
        transforms.ToTensor(),
        normalize
    ])

pretrained_net = models.resnet18(pretrained=False)
pretrained_net.load_state_dict(torch.load('/home/kesci/input/resnet185352/resnet18-5c106cde.pth'))
pretrained_net.fc = nn.Linear(512, 2)

output_params = list(map(id, pretrained_net.fc.parameters()))
feature_params = filter(lambda p: id(p) not in output_params, pretrained_net.parameters())

lr = 0.01
optimizer = optim.SGD([{'params': feature_params},
                       {'params': pretrained_net.fc.parameters(), 'lr': lr * 10}],lr=lr, weight_decay=0.001)

def train_fine_tuning(net, optimizer, batch_size=128, num_epochs=5):
    train_iter = DataLoader(ImageFolder(os.path.join(data_dir, 'hotdog/train'), transform=train_augs),
                            batch_size, shuffle=True)
    test_iter = DataLoader(ImageFolder(os.path.join(data_dir, 'hotdog/test'), transform=test_augs),
                           batch_size)
    loss = torch.nn.CrossEntropyLoss()
    d2l.train(train_iter, test_iter, net, loss, optimizer, device, num_epochs)
        
train_fine_tuning(pretrained_net, optimizer)