pytorch-12-多分类实战

最新推荐文章于 2025-09-26 12:23:22 发布

原创

最新推荐文章于 2025-09-26 12:23:22 发布 · 757 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #pytorch

本文介绍了在PyTorch中进行多分类任务的实战，分别展示了使用底层函数和高阶API的操作。在使用底层函数时，通过训练结果分析发现损失未下降可能源于权重初始化问题，启用合适的权重初始化方法后，损失有所改善。接着，文章提供了使用高阶API的代码实现，简化了操作流程。

多分类实战

1、使用低层函数的操作
2、使用高阶API实现

1、使用低层函数的操作

在这里插入图片描述

实战代码

import  torch
import  torch.nn as nn
import  torch.nn.functional as F
import  torch.optim as optim
from    torchvision import datasets, transforms


batch_size=200
learning_rate=0.01
epochs=10

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./MNIST_data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./MNIST_data', train=False, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])),
    batch_size=batch_size, shuffle=True)



w1, b1 = torch.randn(200, 784, requires_grad=True),\
         torch.zeros(200, requires_grad=True)
w2, b2 = torch.randn(200, 200, requires_grad=True),\
         torch.zeros(200, requires_grad=True)
w3, b3 = torch.randn(10, 200, requires_grad=True),\
         torch.zeros(10, requires_grad=True)

# torch.nn.init.kaiming_normal_(w1)
# torch.nn.init.kaiming_normal_(w2)
# torch.nn.init.kaiming_normal_(w3)


def forward(x):
    x = x@w1.t() + b1
    x = F.relu(x)
    x = x@w2.t() + b2
    x = F.relu(x)
    x = x@w3.t() + b3
    x = F.relu(x)
    return x



optimizer = optim.SGD([w1, b1, w2, b2, w3, b3], lr=learning_rate)
criteon = nn.CrossEntropyLoss()

for epoch in range(epochs):

    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28*28)

        logits = forward(data)
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        # print(w1.grad.norm(), w2.grad.norm())
        optimizer.step()

        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))


    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        logits = forward(data)
        test_loss += criteon(logits, target).item()

        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).sum()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

训练结果
在这里插入图片描述
Note：由训练结果可以看出来，损失一直没有下降，导致损失不下降的原因有多方面，比如：