pytorch3--过拟合、交叉验证

目录

一.过拟合

1.欠拟合，过拟合

how to detect overfitting

二.Train-Val-Test

1.划分Train-Val-Test

2.实现代码

3.交叉验证，k-fold cross validation

---

---

一.过拟合

1.欠拟合，过拟合

Estimated<Groud-truth,Underfitting

Estimated>Groud-truth,Underfitting,Overfitting

• how to detect overfitting

• how to reduce

二.Train-Val-Test

(how to detect overfitting)

train test trade-off

1.划分Train-Val-Test

2.实现代码

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=0.001
epochs=10
 
#加载数据
train_db = datasets.MNIST('../data', train=True, download=True,
                          transform=transforms.Compose([
                              transforms.ToTensor(),
                              transforms.Normalize((0.1307,), (0.3081,))
                          ]))
train_loader = torch.utils.data.DataLoader(
    train_db,
    batch_size=batch_size,shuffle = True
)
test_db = datasets.MNIST('../data', train=False, transform=transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
]))
test_loader = torch.utils.data.DataLoader(
    test_db,
    batch_size=batch_size, shuffle=True
)

print('train:', len(train_db), 'test:', len(test_db))
#把train_db分为train_db, val_db
train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000])
print('db1:', len(train_db), 'db2:', len(val_db))

#重新分配下载train_loader，val_loader；之前已分配下载好test_loader
train_loader = torch.utils.data.DataLoader(
    train_db,
    batch_size=batch_size, shuffle=True)
val_loader = torch.utils.data.DataLoader(
    val_db,
    batch_size=batch_size, shuffle=True)

 
#MLP的model
class MLP(nn.Module):
    def __init__(self):
        super(MLP,self).__init__()
        self.model = nn.Sequential(
            nn.Linear(784,200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200,200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200,10),
            nn.LeakyReLU(inplace=True),
            
        )
        
    def forward(self,x):
        x = self.model(x)
        return x
 
device = torch.device('cuda:0')
net = MLP().to(device)
optimizer = optim.SGD(net.parameters(),lr = learning_rate)
criteon = nn.CrossEntropyLoss().to(device)
'''net = MLP()
optimizer = optim.SGD(net.parameters(),lr=learning_rate)
criteon = nn.CrossEntropyLoss()'''
 
#train
for epoch in range(epochs):
    for batch_idx,(data,target) in enumerate(train_loader):
        data = data.view(-1,28*28)
        data, target = data.to(device),target.to(device)#GPU加速时补
        
        logits = net(data)
        loss = criteon(logits,target)
        
        optimizer.zero_grad()
        loss.backward()
        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()))
            
 
 #validation
    test_loss = 0
    correct = 0
    for data, target in val_loader:
        data = data.view(-1, 28 * 28)
        data, target = data.to(device), target.to(device)
        logits = net(data)
        test_loss += criteon(logits, target).item()

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

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

#人为监视，选择最好的参数，此处加载最好的参数，使用test_loader数据集做test

#test   
    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1,28*28)
        data, target = data.to(device),target.to(device)#GPU加速时补
        logits = net(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)))

3.交叉验证，k-fold cross validation

将train数据集分N份，N-1/N作为train test，1/N作为val test