《动手学习深度学习》之五：CV案例（案例1：Kaggle CIFAR-10 图像分类竞赛与案例2：Kaggle Dog Breed Identification 图像分类竞赛）（打卡3.2）

CV案例

1.案例1：Kaggle CIFAR-10 图像分类竞赛

1.1.导入包和模块

# 可以在Kaggle访问：
# https://www.kaggle.com/boyuai/boyu-d2l-image-classification-cifar-10
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import os
import time

print("PyTorch Version: ",torch.__version__)

1.2.获取和组织数据集

1.2.1.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。
1.2.2.为了更容易上手，我们提供了上述数据集的小样本。“ train_tiny.zip”包含 80 训练样本，而“ test_tiny.zip”包含100个测试样本。它们的未压缩文件夹名称分别是“ train_tiny”和“ test_tiny”。

1.3.图像增强

data_transform = transforms.Compose([
    transforms.Resize(40),
    transforms.RandomHorizontalFlip(),
    transforms.RandomCrop(32),
    transforms.ToTensor()
])
trainset = torchvision.datasets.ImageFolder(root='/home/kesci/input/CIFAR102891/cifar-10/train'
                                            , transform=data_transform)


trainset[0][0].shape

data = [d[0].data.cpu().numpy() for d in trainset]
np.mean(data)
np.std(data)

# 图像增强
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((0.4731, 0.4822, 0.4465), (0.2212, 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((0.4731, 0.4822, 0.4465), (0.2212, 0.1994, 0.2010)),
])

1.4.导入数据集

train_dir = '/home/kesci/input/CIFAR102891/cifar-10/train'
test_dir = '/home/kesci/input/CIFAR102891/cifar-10/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']

1.5.定义模型

1.5.1.ResNet-18网络结构：ResNet全名Residual Network残差网络
1.5.2.

class ResidualBlock(nn.Module):   # 我们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，是一种人工神经网络中常用的激活函数
            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)