超详细PyTorch实现手写数字识别器的示例代码

import torch
import torchvision
import torchvision.transforms as transforms
import numpy as np
import matplotlib.pyplot as plt

transform = transforms.Compose([
  transforms.ToTensor(),
  transforms.Normalize((0.5), (0.5))
])
trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True,num_workers=2)

norm_data = (tensor - mean) / std

def imshow(img):
   img = img / 2 + 0.5 # unnormalize
   npimg = img.numpy()
   plt.imshow(np.transpose(npimg, (1, 2, 0)))
   plt.show()
# torchvision.utils.make_grid 将图片进行拼接
imshow(torchvision.utils.make_grid(iter(trainloader).next()[0]))

from torch import nn
import torch.nn.functional as F
class Net(nn.Module):
  def __init__(self):
    super(Net, self).__init__()
    self.conv1 = nn.Conv2d(in_channels=1, out_channels=28, kernel_size=5) # 14
    self.pool = nn.MaxPool2d(kernel_size=2, stride=2) # 无参数学习因此无需设置两个
    self.conv2 = nn.Conv2d(in_channels=28, out_channels=28*2, kernel_size=5) # 7
    self.fc1 = nn.Linear(in_features=28*2*4*4, out_features=1024)
    self.fc2 = nn.Linear(in_features=1024, out_features=10)
  def forward(self, inputs):
    x = self.pool(F.relu(self.conv1(inputs)))
    x = self.pool(F.relu(self.conv2(x)))
    x = x.view(inputs.size()[0],-1)
    x = F.relu(self.fc1(x))
    return self.fc2(x)

net = Net()
opt = torch.optim.Adam(params=net.parameters(), lr=0.001)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net.to(device)

Net(
 (conv1): Conv2d(1, 28, kernel_size=(5, 5), stride=(1, 1))
 (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
 (conv2): Conv2d(28, 56, kernel_size=(5, 5), stride=(1, 1))
 (fc1): Linear(in_features=896, out_features=1024, bias=True)
 (fc2): Linear(in_features=1024, out_features=10, bias=True)
)

for epoch in range(50):
  for images, labels in trainloader:
    images = images.to(device)
    labels = labels.to(device)
    pre_label = net(images)
    loss = F.cross_entropy(input=pre_label, target=labels).mean()
    pre_label = torch.argmax(pre_label, dim=1)
    acc = (pre_label==labels).sum()/torch.tensor(labels.size()[0], dtype=torch.float32)
    net.zero_grad()
    loss.backward()
    opt.step()
  print(acc.detach().cpu().numpy(), loss.detach().cpu().numpy())

acc = (pre_label==labels).sum()/torch.tensor(labels.size()[0], dtype=torch.float32)
# pre_label==labels 相同维度进行比较相同返回True不同的返回False，True为1 False为0, 即可获取到相等的个数，再除总个数，就得到了Accuracy准确度了

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=True,num_workers=2)
images, labels = iter(testloader).next()
images = images.to(device)
labels = labels.to(device)
with torch.no_grad():
  pre_label = net(images)
  pre_label = torch.argmax(pre_label, dim=1)
  acc = (pre_label==labels).sum()/torch.tensor(labels.size()[0], dtype=torch.float32)
  print(acc)