cifar10分类学习笔记

动⼿实战CIFAR-10图像分类问题，本次实验基于pytorch
Kaggle⽐赛的⽹⻚地址是https://www.kaggle.com/c/cifar-10 。

从网站上可以下载得到对应得数据集，比赛数据分为训练集和测试集。训练集包含 50,000 图片。测试集包含 300,000 图片。两个数据集中的图像格式均为PNG，高度和宽度均为32像素，并具有三个颜色通道（RGB）。图像涵盖10个类别：飞机，汽车，鸟类，猫，鹿，狗，青蛙，马，船和卡车。
下载完训练数据集train.7z和测试数据集test.7z后需要解压缩。解压缩后，将训练数据集、测试数据集以及训练数据集标签分别存放在以下3个路径：
• …/data/cifar10/train/train/[1-50000].png；
• …/data/cifar10/test/test/[1-300000].png；
• …/data/cifar10/trainLabels.csv。
数据的预处理，归一化，图像增广处理，提高模型的过拟合能力

import torch
import torchvision
from torchvision import datasets, transforms


transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),  #先四周填充0，再把图像随机裁剪成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)),
])

train_dir = '/home/deeplearning/cifar10/data/train'
test_dir = '/home/deeplearning/cifar10/data/test'

trainset = torchvision.datasets.ImageFolder(root=train_dir, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=256, shuffle=True)

testset = torchvision.datasets.ImageFolder(root=test_dir, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=256, shuffle=False)

classes = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'forg', 'horse', 'ship', 'truck']

采用的模型，ResNet-18网络结构：ResNet全名Residual Network残差网络

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

class ResidualBlock(nn.Module):   # 定义网络时一般是继承的torch.nn.Module创建新的子类

    def __init__(self, inchannel, outchannel, stride=1):
        super(ResidualBlock, self).__init__()
        #torch.nn.Sequential是一个Sequential容器，模块将按照构造函数中传递的顺序添加到模块中。
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=stride, padding=1, bias=False),
            # 添加第一个卷积层,调用了nn里面的Conv2d（）
            nn.BatchNorm2d(outchannel), # 进行数据的归一化处理
            nn.ReLU(inplace=True), # 修正线性单元，一种常用的激活函数
            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)
            )
        #  便于之后的联合,要判断Y = self.left(X)的形状是否与X相同

    def forward(self, x): # 将两个模块的特征进行结合，并使用ReLU激活函数得到最终的特征。
        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( # 用3个3x3的卷积核代替7x7的卷积核，减少模型参数
            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)   #第一个ResidualBlock的步幅由make_layer的函数参数stride指定
        # ，后续的num_blocks-1个ResidualBlock步幅是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)

训练的代码

import torch
import torch.nn as nn
import torch.optim as optim
import model
import dataload
import argparse
parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--outf', default='./checkpoint', help='folder to output images and model checkpoints') #输出结果保存路径
args = parser.parse_args()


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

# 超参数设置
EPOCH = 2  # 遍历数据集次数
pre_epoch = 0  # 定义已经遍历数据集的次数
LR = 0.1  # 学习率

# 模型定义-ResNet
net = model.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__":
    print("Start Training, Resnet-18!")
    num_iters = 0
    for epoch in range(pre_epoch, EPOCH):
        print('\nEpoch: %d' % (epoch + 1))
        net.train()
        sum_loss = 0.0
        correct = 0.0
        total = 0
        for i, data in enumerate(dataload.trainloader, 0):
            # 用于将一个可遍历的数据对象(如列表、元组或字符串)组合为一个索引序列，同时列出数据和数据下标，
            # 下标起始位置为0，返回 enumerate(枚举) 对象。

            num_iters += 1
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)
            optimizer.zero_grad()  # 清空梯度

            # forward + backward
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            sum_loss += loss.item() * labels.size(0)
            _, predicted = torch.max(outputs, 1)  # 选出每一列中最大的值作为预测结果
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            # 每20个batch打印一次loss和准确率
            if (i + 1) % 20 == 0:
                print('[epoch:%d, iter:%d] Loss: %.03f | Acc: %.3f%% '
                      % (epoch + 1, num_iters, sum_loss / (i + 1), 100. * correct / total))
		#测试准确率
        with torch.no_grad():
            correct = 0
            total = 0
            for data in dataload.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
            # 保存模型
            print('Saving model......')
            torch.save(net.state_dict(), '%s/net_%03d.pth' % (args.outf, epoch + 1))
        
    print("Training Finished, TotalEPOCH=%d" % EPOCH)

运行的结果：
第二个epoch里acc就到了100%，感觉似乎存在问题，欢迎指教