【Pytorch✨】神经网络训练分类器

训练一个分类器

训练流程如下：

1. 采用 torchvision 加载和归一化 CIFAR10 训练集和测试集数据；
2. 定义一个卷积神经网络
3. 定义损失函数
4. 在训练集上训练
5. 在测试集上测试模型

1. 加载并归一化 CIFAR10

import torch
import torchvision 
import torchvision.transforms as transforms

加载数据集data

batch_size: 加载数据集大小 (类似一维数组大小)

#数据集大小
num_size = 4
# 将图片数据从 [0,1] 归一化为 [-1, 1] 的取值范围
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=num_size, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=num_size, shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

可能出现问题：

解决方法：用另一个虚拟环境跑

#展示数据集图片
import matplotlib.pyplot as plt
import numpy as np

#展示图片的函数
def imshow(img):
    img = img / 2 + 0.5
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()
    
#随机获取训练数据集图片
dataiter = iter(trainloader)
images, labels = next(dataiter)
print('图片的标签: ', labels)
imshow(torchvision.utils.make_grid(images))

#打印图片类别标签 
#TODO:为什么固定为4是会报错
print(' '.join('%5s' % classes[labels[j]] for j in range(num_size)))

如果出现内核崩溃可以尝试以下方法：

2. 定义一个卷积神经网络

import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3,6,5)
        self.pool = nn.MaxPool2d(2,2)
        self.conv2 = nn.Conv2d(6,16,5)
        self.fc1 = nn.Linear(16*5*5,120)
        self.fc2 = nn.Linear(120,84)
        self.fc3 = nn.Linear(84,10)
    def forward(self,x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1,16*5*5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
net = Net()

3. 定义损失函数

import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

4. 训练网络

import time
start = time.time()
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!Total cost time:',time.time()-start)

5. 测试模型效果

dataiter = iter(testloader)
#images,labels = dataiter.next() #false
images,labels = next(dataiter) #true
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s'%classes[labels[j]] for j in range(num_size)))
# 网络输出
outputs = net(images)
print('outputs:',outputs)
print('predict:',torch.max(outputs, 1))
_, predicted = torch.max(outputs, 1)
print('Predicted:',''.join('%5s'%classes[predicted[j]] for j in range(num_size)))