pytorch--CIFAR-10

本期我们来利用pytorch深度学习框架进行CIFAR-10项目实践。从本文你将要学到

• 如何利用torchvision.datasets读取远程数据

CIFAR-10图像分类项目

• 背景
• 读取数据并可视化
• 构建网络，损失函数，优化方式
• 模型训练
• 评估模型
• 保存模型
• 加载模型做测试
• 参考文献

背景

CIFAR-10是kaggle计算机视觉竞赛的一个图像分类项目。该数据集共有60000张32*32彩色图像，一共可以分为"plane", “car”, “bird”,“cat”, “deer”, “dog”, “frog”,“horse”,“ship”, “truck” 10类，每类6000张图。有50000张用于训练，构成了5个训练批，每一批10000张图；10000张用于测试，单独构成一批。

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
               [transforms.ToTensor(),
               transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root = './data', train =True, download = True, transform = transform)
trainloader =torch.utils.data.DataLoader(trainset, batch_size =4, shuffle = True, num_workers = 0)
testset = torchvision.datasets.CIFAR10(root = './data', train = False, download = True, transform = transform)
testloader = torch.utils.data.DataLoader(testset, batch_size = 4, shuffle = False, num_workers = 0)
classes = ("plane", "car", "bird","cat", "deer", "dog", "frog","horse","ship", "truck")


import matplotlib.pyplot as plt
import numpy as np

def imShow(img):
    img = img /2 + 0.5
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1,2,0)))
    plt.show()
    
dataiter =iter(trainloader)
images, labels = dataiter.next()
imShow(torchvision.utils.make_grid(images))
print(" ".join("%5s" % classes[labels[j]] for j in range(4)))  
           

• 输出结果

Files already downloaded and verified

Files already downloaded and verified

truck car frog plane

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

class Net(nn.Module): #继承的torch.nn.Module类
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5) #添加第一个卷积层,调用了nn里面的Conv2d()
        self.pool = nn.MaxPool2d(2, 2) #添加最大池化层
        self.conv2 = nn.Conv2d(6, 16, 5) #添加第二个卷积层
        self.fc1 = nn.Linear(16*5*5, 120) #第一个全连接层
        self.fc2 = nn.Linear(120, 84) #第二个全连接层
        self.fc3 = nn.Linear(84, 10) #第三个全连接层
        
    def forward(self, x): #定义向前传播方法
        x = self.pool(F.relu(self.conv1(x))) #relu激活第一个卷积层
        x = self.pool(F.relu(self.conv2(x))) #relu激活第二个卷积层
        x = x.view(-1, 16*5*5) #重构张量的维度
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    
net = Net() #网络实例化
criterion = nn.CrossEntropyLoss() #定义损失函数为交叉熵损失函数
optimizer = optim.SGD(net.parameters(), lr = 0.001, momentum = 0.9)  #定义优化方式为机梯度下降
           

for epoch in range(2):
    
    running_loss =0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i%2000 == 1999:
            print('[%d, %5d] loss: %.3f' %  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0            
print("Finished Training")  
           

correct = 0 
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels =data
        outputs = net(images)
        _, predicted  = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct +=(predicted==labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1
for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))
           

PATH =".cifar10_net.pth"
torch.save(net.state_dict(), PATH)
           

net = Net()
net.load_state_dict(torch.load(PATH))

outputs = net(images)

_, predicted = torch.max(outputs, 1)
print("predicted: ", " ".join("%5s" % classes[predicted[j]] for j in range(4)))