动手学深度学习PyTorch版-微调

微调

热狗识别

%matplotlib inline
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')

data_dir = '/home/kesci/input/hotdog4014'
os.listdir(os.path.join(data_dir, "hotdog"))

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
    ])

定义和初始化模型

pretrained_net = models.resnet18(pretrained=False)
pretrained_net.load_state_dict(torch.load('/home/kesci/input/resnet185352/resnet18-5c106cde.pth'))

print(pretrained_net.fc)

pretrained_net.fc = nn.Linear(512, 2)
print(pretrained_net.fc)

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)

模型微调

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)

scratch_net = models.resnet18(pretrained=False, num_classes=2)
lr = 0.1
optimizer = optim.SGD(scratch_net.parameters(), lr=lr, weight_decay=0.001)
train_fine_tuning(scratch_net, optimizer)