pytorch-train&val&test划分

1. 上一节回顾

下列图中三种曲线分别代表了欠拟合、好的拟合和过拟合

下图为过拟合曲线，那么如何来检测过拟合呢？将数据集划分为train和val（validation）val是用来测试训练过程是否过拟合的。

2. 数据集划分

数据集一般划分为train、val（当划分为2个数据集时，val又被称为test）、test
以MINIST数据集为例，下图中将数据集化为为train和test(val)

下图中每train一个epoch就进行依次test看是否发生了过拟合，并保存当时的checkpoint，训练完成后选择性能最好的checkpoints即可。

下图中在标记点之后train的loss变换不明显，而test loss却升高了，这就是发生了overfitting过拟合。

如下图：假如又70k数据train50k，val10k,test10k，那么为什么要又test数据集呢？作用是什么呢？test数据集是用来验证模型的性能的，不能用于train和val否则会造成数据污染，也可称为作弊。

pytorch只能划分train和test，即通过train_db = datasets.MNIST('../data', train=True, download=True, 中的train=true即为train数据集，否则为test数据集 ，那么剩下的train我们要人为划分为train和val。
如下图所示：通过train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000]) 实现把train划分为train50k，val10k

总结：train数据用来训练，val数据用来检测训练是否过拟合的，test数据集是用来验证模型性能的

3. 完整代码

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_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))
train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000])
print('db1:', len(train_db), 'db2:', len(val_db))
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)




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)

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.cuda()

        logits = net(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 val_loader:
        data = data.view(-1, 28 * 28)
        data, target = data.to(device), target.cuda()
        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)))



test_loss = 0
correct = 0
for data, target in test_loader:
    data = data.view(-1, 28 * 28)
    data, target = data.to(device), target.cuda()
    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)))