pytorch网络搭建和MNIST数据集训练代码

说一下踩坑的地方

1.transforms.Totensor并未归一化训练集，因此额外除了255.0，以此归一化

2.tensorboardX安装时先安装tensorboard,再安装tensorboardX

3.标签独热编码后出现valueerror，也没解决

4.pytorch bug太多，不太好用

代码如下

import torch
import torch.nn as nn
from tensorboardX import SummaryWriter
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5), (0.5))
])
train_dataset = datasets.MNIST(root='./data/MNIST1', train=True,
                               download=False, transform=transform)
test_dataset = datasets.MNIST(root='./data/MNIST1', train=False,
                             download=False, transform=transform)

train_dataset.data=train_dataset.data.type(torch.FloatTensor)/255.0
test_dataset.data=test_dataset.data.type(torch.FloatTensor)/255.0

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=1000, shuffle=False)

class Convnet(nn.Module):
    def __init__(self):
        super(Convnet,self).__init__()
        self.conv1=nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=10,
                kernel_size=(5,5),
            ),
            nn.ReLU(),
            nn.MaxPool2d(
                kernel_size=2,
            )
        )
        self.conv2=nn.Sequential(
            nn.Conv2d(10,20,5),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2)
        )
        self.fc=nn.Sequential(
            nn.Linear(
                in_features=320,
                out_features=160
            ),
            nn.ReLU(),
            nn.Linear(160,80),
            nn.ReLU(),
            nn.Linear(80,40),
            nn.ReLU()
        )
        self.out=nn.Linear(40,10)
    def forward(self,x):
        x=self.conv1(x)
        x=self.conv2(x)
        x=x.view(x.size(0),-1)
        x=self.fc(x)
        output=self.out(x)
        return output
model = Convnet()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01,momentum=0.5)
num_epochs = 10
sw=SummaryWriter(logdir='data/chap4/log')

for epoch in range(num_epochs):
    model.train()
    running_loss = 0.0
    for images, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    print(f'Epoch [{epoch+1}/{num_epochs}, '
          f'Loss: {running_loss/len(train_loader):.4f}')
    sw.add_scalar('running_loss',
                  running_loss/len(train_loader),global_step=epoch)
  
    model.eval()
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in test_loader:
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

        print(f'Accuracy of the network on the 10000 test images: '
              f'{100 * correct / total}%')
        sw.add_scalar('test_acc',correct / total,epoch)

可视化在tensorboard里看，终端输入 tensorboard --logdir="文件名"，然后打开它给的网址