ResNet-18实现Cifar-10图像分类

CIFAR-10

该数据集共有60000张彩色图像,这些图像尺寸是32 * 32,分为10个类,每类6000张图。这里面有50000张用于训练,构成了5个训练批,每一批10000张图;另外10000用于测试,单独构成一批。测试批的数据里,取自10类中的每一类,每一类随机取1000张。抽剩下的就随机排列组成了训练批。注意一个训练批中的各类图像并不一定数量相同,总的来看训练批,每一类都有5000张图。

下面这幅图就是列举了10各类,每一类展示了随机的10张图片: cifar-10

ResNet-18网络结构

resnet18 ResNet全名Residual Network残差网络。Kaiming He 的《Deep Residual Learning for Image Recognition》获得了CVPR最佳论文。他提出的深度残差网络在2015年可以说是洗刷了图像方面的各大比赛,以绝对优势取得了多个比赛的冠军。而且它在保证网络精度的前提下,将网络的深度达到了152层,后来又进一步加到1000的深度。论文的开篇先是说明了深度网络的好处:特征等级随着网络的加深而变高,网络的表达能力也会大大提高。因此论文中提出了一个问题:是否可以通过叠加网络层数来获得一个更好的网络呢?作者经过实验发现,单纯的把网络叠起来的深层网络的效果反而不如合适层数的较浅的网络效果。因此何恺明等人在普通平原网络的基础上增加了一个shortcut, 构成一个residual block。此时拟合目标就变为F(x),F(x)就是残差: fx1

Pytorch上搭建ResNet-18

'''ResNet-18 Image classfication for cifar-10 with PyTorch 

Author 'Sun-qian'.

'''
import torch
import torch.nn as nn
import torch.nn.functional as F


class ResidualBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(ResidualBlock, self).__init__()
        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:
            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)
        out += self.shortcut(x)
        out = F.relu(out)
        return out


class ResNet(nn.Module):
    def __init__(self, ResidualBlock, 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(ResidualBlock, 64,  2, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 2, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 2, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 2, stride=2)
        self.fc = nn.Linear(512, num_classes)


    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)   #strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):
        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

    def ResNet18():
        return ResNet(ResidualBlock)

Pytorch上训练

训练时动态调整学习率,当epoch:[1-135] ,lr=0.1;epoch:[136-185], lr=0.01;epoch:[186-240] ,lr=0.001。训练代码如下:

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import argparse
from resnet import ResNet18
import os


# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 参数设置,使得我们能够手动输入命令行参数,就是让风格变得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--outf', default='./model/', help='folder to output images and model checkpoints') #输出结果保存路径
args = parser.parse_args()

# 超参数设置
EPOCH = 135   #遍历数据集次数
pre_epoch = 0  # 定义已经遍历数据集的次数
BATCH_SIZE = 128      #批处理尺寸(batch_size)
LR = 0.01        #学习率


# 准备数据集并预处理
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),  #先四周填充0,在吧图像随机裁剪成32*32
    transforms.RandomHorizontalFlip(),  #图像一半的概率翻转,一半的概率不翻转
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), #R,G,B每层的归一化用到的均值和方差
])

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

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train) #训练数据集
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)   #生成一个个batch进行批训练,组成batch的时候顺序打乱取

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
# Cifar-10的标签
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# 模型定义-ResNet
net = ResNet18().to(device)

# 定义损失函数和优化方式
criterion = nn.CrossEntropyLoss()  #损失函数为交叉熵,多用于多分类问题
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4) #优化方式为mini-batch momentum-SGD,并采用L2正则化(权重衰减)


# 训练
if __name__ == "__main__":
    if not os.path.exists(args.outf):
        os.makedirs(args.outf)
    best_acc = 85  #2 初始化best test accuracy
    print("Start Training, Resnet-18!")  # 定义遍历数据集的次数
    with open("acc.txt", "w") as f:
        with open("log.txt", "w")as f2:
            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):
                    # 准备数据
                    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()

                    # 每训练1个batch打印一次loss和准确率
                    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))
                    f2.write('%03d  %05d |Loss: %.03f | Acc: %.3f%% '
                          % (epoch + 1, (i + 1 + epoch * length), sum_loss / (i + 1), 100. * correct / total))
                    f2.write('\n')
                    f2.flush()

                # 每训练完一个epoch测试一下准确率
                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)
                        # 取得分最高的那个类 (outputs.data的索引号)
                        _, predicted = torch.max(outputs.data, 1)
                        total += labels.size(0)
                        correct += (predicted == labels).sum()
                    print('测试分类准确率为:%.3f%%' % (100 * correct / total))
                    acc = 100. * correct / total
                    # 将每次测试结果实时写入acc.txt文件中
                    print('Saving model......')
                    torch.save(net.state_dict(), '%s/net_%03d.pth' % (args.outf, epoch + 1))
                    f.write("EPOCH=%03d,Accuracy= %.3f%%" % (epoch + 1, acc))
                    f.write('\n')
                    f.flush()
                    # 记录最佳测试分类准确率并写入best_acc.txt文件中
                    if acc > best_acc:
                        f3 = open("best_acc.txt", "w")
                        f3.write("EPOCH=%d,best_acc= %.3f%%" % (epoch + 1, acc))
                        f3.close()
                        best_acc = acc
            print("Training Finished, TotalEPOCH=%d" % EPOCH)

最后实验结果:best_acc= 95.170% accu

本文来源:

results matching ""

    No results matching ""