Pytorch学习4

深入理解PyTorch：实战篇

最新推荐文章于 2023-08-19 14:56:24 发布

weixin_39287932

最新推荐文章于 2023-08-19 14:56:24 发布

阅读量238

点赞数 1

CC 4.0 BY-SA版权

文章标签： Pytorch学习

本文链接：https://blog.youkuaiyun.com/weixin_39287932/article/details/90349908

本文将深入探讨PyTorch的使用技巧，通过实际案例解析其核心概念，包括动态计算图、张量操作、神经网络构建以及优化器的应用。无论你是初学者还是进阶者，都能从中获得关于PyTorch的宝贵知识。

导入相关模块
import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# GPU配置
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 超参数
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# 手写数字集
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# 数据加载
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# 两层CNN网络
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7*7*32, num_classes)
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model = ConvNet(num_classes).to(device)

# 损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 训练
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        #前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 后向传播、优化求解
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型测试
model.eval()  
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('准确率: {} %'.format(100 * correct / total))