pytorch之resnet18模型保存再训练

• 参考这里写的
• 学习率0.01在测试集上最高89%的准确率
• 增加了测试集准确率的记录，多次降低学习率，0.000001时最高准确率93%

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import os, cv2
from PIL import Image
from tensorboardX import SummaryWriter

class MyData(torch.utils.data.Dataset):
    def __init__(self, train=True, transform=None, target_transform=None):
        self.transform = transform
        self.target_transform = target_transform
        self.train = train
        if self.train:
            data_file = "/home/lwd/data/cifar10/train/train.txt"
        else:
            data_file = "/home/lwd/data/cifar10/test/test.txt"
        self.data=[]
        self.targets = []
        cnt = 0
        for line in open(data_file):
            str_list = line.split()
            img = cv2.imread(str_list[0])
            # img = cv2.resize(img, (224,224), interpolation=cv2.INTER_AREA)
            self.data.append(img)
            self.targets.append(str_list[1])
            cnt+=1
            if(cnt % 10000 == 0):
                print(cnt)

    def __getitem__(self, index):
        img, target = self.data[index], int(self.targets[index])
        img = Image.fromarray(img)
        if self.transform is not None:
            img = self.transform(img)
        if self.target_transform is not None:
            target = self.target_transform(target)
        return img, target

    def __len__(self):
        return len(self.data)

#定义残差块ResBlock
class ResBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(ResBlock, self).__init__()
        #这里定义了残差块内连续的2个卷积层
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU(inplace=True),
            nn.Conv2d(outchannel, outchannel, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(outchannel)
        )
        self.shortcut = nn.Sequential()
        if stride != 1 or inchannel != outchannel:
            #shortcut，这里为了跟2个卷积层的结果结构一致，要做处理
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )
            
    def forward(self, x):
        out = self.left(x)
        #将2个卷积层的输出跟处理过的x相加，实现ResNet的基本结构
        out = out + self.shortcut(x)
        out = F.relu(out)
        
        return out

class ResNet(nn.Module):
    def __init__(self, ResBlock, num_classes=10):
        super(ResNet, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU()
        )
        self.layer1 = self.make_layer(ResBlock, 64, 2, stride=1)
        self.layer2 = self.make_layer(ResBlock, 128, 2, stride=2)
        self.layer3 = self.make_layer(ResBlock, 256, 2, stride=2)        
        self.layer4 = self.make_layer(ResBlock, 512, 2, stride=2)        
        self.fc = nn.Linear(512, num_classes)
    #这个函数主要是用来，重复同一个残差块    
    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        # print(*layers)
        return nn.Sequential(*layers)
    def forward(self, x):
        #在这里，整个ResNet18的结构就很清晰了
        out = self.conv1(x)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = F.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
log_dir = './snapshot/'
last = 0
ptt = 92
pth='/home/lwd/Downloads/5/snapshot/'+str(ptt)+'.pth'
writer = SummaryWriter('./resnet_result')

#set hyperparameter
EPOCH = 1000
pre_epoch = 0
BATCH_SIZE = 128
LR = 0.01

#prepare dataset and preprocessing
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])

trainset = MyData(train=True, transform=transform_train)
# trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True)

testset = MyData(train=False, transform=transform_test)
# testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False)

#labels in CIFAR10
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

#define ResNet18
net = ResNet(ResBlock).to(device)

#define loss funtion & optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4)

if os.path.exists(pth):
    checkpoint = torch.load(pth)
    net.load_state_dict(checkpoint['model'])
    optimizer.load_state_dict(checkpoint['optimizer'])
    pre_epoch = checkpoint['epoch']
    last = ptt / 100.0

#train
for epoch in range(pre_epoch, EPOCH):
    print('\nEpoch: %d' % (epoch + 1))
    net.train()
    sum_loss = 0.0
    correct = 0.0
    total = 0.0
    for i, data in enumerate(trainloader, 0):
        #prepare dataset
        length = len(trainloader)
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        
        #forward & backward
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        #print ac & loss in each batch
        sum_loss += loss.item()
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += predicted.eq(labels.data).cpu().sum()
        print('[epoch:%d, iter:%d] Loss: %.03f | Acc: %.3f%% ' 
              % (epoch + 1, (i + 1 + epoch * length), sum_loss / (i + 1), 100. * correct / total))
        
    #get the ac with testdataset in each epoch
    print('Waiting Test...')
    with torch.no_grad():
        correct = 0
        total = 0
        for data in testloader:
            net.eval()
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum()
        print('Test\'s ac is: %.3f%%' % (100 * torch.true_divide(correct, total)))
    now = (100. * correct / total).item()
    writer.add_scalars('acc', {'test_acc': now}, epoch)
    if now > last:
        state = {'model':net.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch':epoch}
        torch.save(state, log_dir+str(int(now))+'.pth')
        last = now
        # break