pytorch-解决过拟合之early stop和dropout

1. Early Stop

所谓的over fitting是训练集准确率在上升，但是test准确率开始下降了。

在测试集准确率达到最高点开始下降的时候停止训练，以防止over fitting

2. 怎样Early Stop

用验证机来选择模型参数
监测验证集的性能
在性能最高点时停止训练

3. Dropout

Dropout就是使用一个概率来减少模型参数量，使得模型复杂度降低，从而降低over fitting的几率。

模型复杂度越低over fitting的几率也就越低，因此Dropout通过使某些连接p=wx=0，相当于断掉该条连接，从而减少了当前层到下一层的连接数。比如：有10k个连接，加了Dropout可能就变成了5k。

4. pytorch实现Dropout

在层与层之间使用torch.nn.Dropout增加Dropout，注意Drop是加在两层之间而不是层内的。

5. train和test时的Dropout

train的时候是可以使用Dropout的，但是test的时候一定不要使用，否则性能会下降，如果train使用了Dropout，那么test的时候要通过net_dropped.eval()取消掉Dropout

6. 增加了vidom的示例代码

python 复制代码

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

from visdom import Visdom

batch_size=200
learning_rate=0.01
epochs=10

train_loader = torch.utils.data.DataLoader(
    datasets.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('../data', train=False, transform=transforms.Compose([
        transforms.ToTensor(),
        # transforms.Normalize((0.1307,), (0.3081,))
    ])),
    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)

viz = Visdom()

viz.line([0.], [0.], win='train_loss', opts=dict(title='train loss'))
viz.line([[0.0, 0.0]], [0.], win='test', opts=dict(title='test loss&acc.',
                                                   legend=['loss', 'acc.']))
global_step = 0

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()

        global_step += 1
        viz.line([loss.item()], [global_step], win='train_loss', update='append')

        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)
        data, target = data.to(device), target.cuda()
        logits = net(data)
        test_loss += criteon(logits, target).item()

        pred = logits.argmax(dim=1)
        correct += pred.eq(target).float().sum().item()

    viz.line([[test_loss, correct / len(test_loader.dataset)]],
             [global_step], win='test', update='append')
    viz.images(data.view(-1, 1, 28, 28), win='x')
    viz.text(str(pred.detach().cpu().numpy()), win='pred',
             opts=dict(title='pred'))

    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)))