Pytorch实例----CAFAR10数据集分类（VGG）

本文主要是介绍Pytorch实例----CAFAR10数据集分类（VGG），希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

在上一篇 Pytorch实例----CAFAR10数据集分类（AlexNet）的识别统计,本篇主要调整Net()类，设计VGG网络（+BN）后的识别统计(其他设计注释同上)。

VGG与AlexNet在CAFAR10数据集的统计结果对比图

可以看到，对于之前cat(19%), bird(33%), truck(47%)有显著提高：cat(50%), bird(42%), truck(80%), 最高识别的类别为：ship(86%), car(81%), frog(80%), turck(80%), 由原来55%的平均识别率提升为71%，各类的识别显著提升。此时的VGG网络仅为VGG11，通过使用VGG16， VGG19有望进一步提升准确率。

VGG网络结构编程实现：

#define the network
cfg = {'VGG11':[64, 'M', 128, 'M', 256, 'M', 512, 'M', 512, 'M'],'VGG13':[64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],'VGG16':[64, 64, 64, 'M', 128, 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
}
class Net(nn.Module):def __init__(self, vgg_name):super(Net, self).__init__()self.features = self._make_layer(cfg[vgg_name])self.classifer = nn.Linear(512, 10)def forward(self, x):out = self.features(x)out = out.view(out.size(0), -1)out = self.classifer(out)return outdef _make_layer(self, cfg):layers = []in_channels = 3for x in cfg:if x == 'M':layers += [nn.MaxPool2d(kernel_size=2, stride=2)]else:layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1, bias=False),nn.BatchNorm2d(x),nn.ReLU(True)]in_channels = xreturn nn.Sequential(*layers)net = Net('VGG11')

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 modelsimport matplotlib.pyplot as plt
import numpy as npdef imshow(img):img = img / 2 + 0.5np_img = img.numpy()plt.imshow(np.transpose(np_img, (1, 2, 0)))#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=4, 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=4, shuffle=True, num_workers=2)
#define class
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')#define the network
cfg = {'VGG11':[64, 'M', 128, 'M', 256, 'M', 512, 'M', 512, 'M'],'VGG13':[64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],'VGG16':[64, 64, 64, 'M', 128, 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
}
class Net(nn.Module):def __init__(self, vgg_name):super(Net, self).__init__()self.features = self._make_layer(cfg[vgg_name])self.classifer = nn.Linear(512, 10)def forward(self, x):out = self.features(x)out = out.view(out.size(0), -1)out = self.classifer(out)return outdef _make_layer(self, cfg):layers = []in_channels = 3for x in cfg:if x == 'M':layers += [nn.MaxPool2d(kernel_size=2, stride=2)]else:layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1, bias=False),nn.BatchNorm2d(x),nn.ReLU(True)]in_channels = xreturn nn.Sequential(*layers)net = Net('VGG11')
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
for epoch in range(2):running_loss = 0.0for i, data in enumerate(trainloader, 0):inputs, labels = datainputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())optimizer.zero_grad()outputs = net(inputs)loss = cost(outputs, labels)loss.backward()optimizer.step()#print loss resultrunning_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 = dataoutputs = 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 = dataoutputs = 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：