Pytorch实例----CAFAR10数据集分类（ResNet）

在上一篇 Pytorch实例----CAFAR10数据集分类（VGG）的识别统计,本篇主要调整Net()类，设计ResNet网络（+BN），实现对CAFAR10分类数据集的分类任务。

ResNet网络结构编程实现：

#create residual block
class ResidualBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(ResidualBlock, self).__init__()
        #define conv2d -> BN -> ReLU -> BN
        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)
        )
        #define shortcut
        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(),
        )
        #use make_layer to append residual block
        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)
    #define use nn.Sequential to create block or stage
    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)
#instance for ResNet18
#net = ResNet18()

整体代码实现：

import torch
import torchvision
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Variable
import torchvision.transforms as transforms
from torchvision import models

import matplotlib.pyplot as plt
import numpy as np

def imshow(img):
    img = img / 2 + 0.5
    np_img = img.numpy()
    plt.imshow(np.transpose(np_img, (1, 2, 0)))
#define Parameter for data
BATCH_SIZE = 4
EPOCH = 4
#define transform
#hint: Normalize(mean, var) to normalize RGB
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5),(0.5, 0.5, 0.5))])
#define trainloader
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)
#define testloader
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)
#define class
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

#create residual block
class ResidualBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(ResidualBlock, self).__init__()
        #define conv2d -> BN -> ReLU -> BN
        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)
        )
        #define shortcut
        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(),
        )
        #use make_layer to append residual block
        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)
    #define use nn.Sequential to create block or stage
    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)

net = ResNet18()
if torch.cuda.is_available():
    net.cuda()
print(net)
#define loss
cost = nn.CrossEntropyLoss()
#define optimizer
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

print('start')
#iteration for training
#setting for epoch
for epoch in range(EPOCH):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = cost(outputs, labels)
        loss.backward()
        optimizer.step()
        
        #print loss result
        running_loss += loss.item()
        if i % 2000 == 1999:
            print('[%d, %5d]  loss: %.3f'%(epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.001
print('done')

#get random image and label
dataiter = iter(testloader)
images, labels = dataiter.next()
#imshow(torchvision.utils.make_grid(images))
print('groundTruth: ', ''.join('%6s' %classes[labels[j]] for j in range(4)))

#get the predict result
outputs = net(Variable(images.cuda()))
_, pred = torch.max(outputs.data, 1)
print('prediction: ', ''.join('%6s' %classes[labels[j]] for j in range(4)))

#test the whole result
correct = 0.0
total = 0
for data in testloader:
    images, labels = data
    outputs = net(Variable(images.cuda()))
    _, pred = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (pred == labels.cuda()).sum()
print('average Accuracy: %d %%' %(100*correct / total))

#list each class prediction
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
for data in testloader:
    images, labels = data
    outputs = net(Variable(images.cuda()))
    _, pred = torch.max(outputs.data, 1)
    c = (pred == labels.cuda()).squeeze()
    for i in range(4):
        label = labels[i]
        class_correct[label] += float(c[i])
        class_total[label] += 1
print('each class accuracy: \n')
for i in range(10):
    print('Accuracy: %6s %2d %%' %(classes[i], 100 * class_correct[i] / class_total[i]))

实验结果：

【注】：随着算力的提升，这里更改了相对较高的training EPOCH, 统计结果如下：

	2	4	8
Loss	0.748(0.789)	0.455	0.152
Acc	74%(71%)	79%	81%

括号表示epoch为2时VGG网络对应的loss和Accuracy，可以看到，随着EPOCH的提升，Loss仍在下降，Accuracy继续提升，当epoch为8时，比VGG提升了10个百分点，表明将残差信息传递给下一级网络能有效避免过拟合和训练困难的问题，在目标检测中，RetinNet及以RetinNet为backbone的网络结构同样采用了该想法，实现了较好的检测效果。

practice makes perfect !

github source code : https://github.com/GinkgoX/CAFAR10_Classification_Task/blob/master/CAFAR10_ResNet.ipynb