基于Python构建深度学习图像分类模型

pip install torch torchvision

pip install matplotlib numpy

import torch
import torchvision
import torchvision.transforms as transforms
 
# 数据预处理
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
 
# 加载训练集和测试集
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=2)
 
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=2)
 
# 类别标签
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

import torch.nn as nn
import torch.nn.functional as F
 
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, 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 = SimpleCNN()

import torch.optim as optim
 
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
#编写训练循环：
python
for epoch in range(2):  # 迭代2个epoch
 
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # 获取输入和标签
        inputs, labels = data
 
        # 将梯度置零
        optimizer.zero_grad()
 
        # 前向传播
        outputs = net(inputs)
        loss = criterion(outputs, labels)
 
        # 反向传播和优化
        loss.backward()
        optimizer.step()
 
        # 打印统计信息
        running_loss += loss.item()
        if i % 2000 == 1999:    # 每2000个mini-batch打印一次
            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))

import matplotlib.pyplot as plt
import numpy as np
 
# 获取一些测试图像及其标签
dataiter = iter(testloader)
images, labels = dataiter.next()
 
# 展示图像及其预测结果
imshow = torchvision.utils.make_grid(images)
imshow = imshow.numpy().transpose((1, 2, 0))
imshow = imshow / 2 + 0.5  # 反归一化
imshow = np.clip(imshow, 0, 1)
 
plt.imshow(imshow)
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
 
# 预测结果
outputs = net(images)
_, predicted = torch.max(outputs, 1)
 
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))
plt.show()