任务5 PyTorch实现L1、L2正则化及Dropout

最新推荐文章于 2024-07-27 20:21:33 发布

qinhanmin

最新推荐文章于 2024-07-27 20:21:33 发布

阅读量522

点赞数

分类专栏：机器学习

本文链接：https://blog.csdn.net/qinhanmin2010/article/details/99638335

版权

本文介绍了如何在PyTorch中实现L1和L2正则化，以及Dropout技术的应用，帮助提升神经网络的泛化能力。

摘要由CSDN通过智能技术生成

L1正则化

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Hyper-parameters 
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.0001
l1_reg = 0.001

# MNIST dataset 
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())

# Data loader
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)

# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Sequential(nn.Linear(input_size, hidden_size),
                                 nn.ReLU())
        self.fc2 = nn.Linear(hidden_size, num_classes)
    
    def forward(self, x):
        out = self.fc1(x)
        out = self.fc2(out)
        return out

model = NeuralNet(input_size, hidden_size, num_classes)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate, weight_decay=l2_reg)  

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader)