使用PyTorch训练一个图像分类器实例

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

print("torch: %s" % torch.__version__)
print("tortorchvisionch: %s" % torchvision.__version__)
print("numpy: %s" % np.__version__)

torch: 1.0.0
tortorchvisionch: 0.2.1
numpy: 1.15.4

transform = transforms.Compose([
  transforms.ToTensor(),
  transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, 
                    download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, 
                     shuffle=True, num_workers=4)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, 
                    download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, 
                     shuffle=True, num_workers=4)
classes = ('plane', 'car', 'bird', 'cat', 
      'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz
Files already downloaded and verified

# 显示一张图片
def imshow(img):
  img = img / 2 + 0.5   # 逆归一化
  npimg = img.numpy()
  plt.imshow(np.transpose(npimg, (1, 2, 0)))
  plt.show()


# 任意地拿到一些图片
dataiter = iter(trainloader)
images, labels = dataiter.next()

# 显示图片
imshow(torchvision.utils.make_grid(images))
# 显示类标
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

truck  dog ship  dog

import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
  def __init__(self):
    super(Net, self).__init__()
    self.conv1 = nn.Conv2d(3, 6, 5)
    self.pool = nn.MaxPool2d(2, 2)
    self.conv2 = nn.Conv2d(6, 16, 5)
    self.fc1 = nn.Linear(16 * 5 * 5, 120)
    self.fc2 = nn.Linear(120, 84)
    self.fc3 = nn.Linear(84, 10)
    
  def forward(self, x):
    x = self.pool(F.relu(self.conv1(x)))
    x = self.pool(F.relu(self.conv2(x)))
    x = x.view(-1, 16 * 5 * 5)
    x = F.relu(self.fc1(x))
    x = F.relu(self.fc2(x))
    x = self.fc3(x)
    return x

net = Net()

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=1e-3, momentum=0.9)

nums_epoch = 2
for epoch in range(nums_epoch):
  _loss = 0.0
  for i, (inputs, labels) in enumerate(trainloader, 0):
    inputs, labels = inputs.to(device), labels.to(device)
    optimizer.zero_grad()
    
    outputs = net(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()
    
    _loss += loss.item()
    if i % 2000 == 1999:  # 每2000步打印一次损失值
      print('[%d, %5d] loss: %.3f' %
         (epoch + 1, i + 1, _loss / 2000))
      _loss = 0.0

print('Finished Training')

[1, 2000] loss: 1.178
[1, 4000] loss: 1.200
[1, 6000] loss: 1.168
[1, 8000] loss: 1.175
[1, 10000] loss: 1.185
[1, 12000] loss: 1.165
[2, 2000] loss: 1.073
[2, 4000] loss: 1.066
[2, 6000] loss: 1.100
[2, 8000] loss: 1.107
[2, 10000] loss: 1.083
[2, 12000] loss: 1.103
Finished Training

# 展示测试数据集
dataiter = iter(testloader)
images, labels = dataiter.next()
imshow(torchvision.utils.make_grid(images))
print('GraoundTruth: ', ' '.join(['%5s' % classes[labels[j]] for j in range(4)]))

GraoundTruth:  ship ship deer ship

# 展示预测值
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join(['%5s' % classes[predicted[j]] for j in range(4)]))

Predicted:  car ship horse ship

# 评估测试数据集
correct, total = 0, 0
with torch.no_grad():
  for images, labels in testloader:
    outputs = net(images)
    _, predicted = torch.max(outputs, 1)
    total += labels.size(0)
    correct += (labels == predicted).sum().item()
  
print('Accuracy of the network on the 10000 test images: %d %%' % (
  100 * correct / total))

Accuracy of the network on the 10000 test images: 58 %

# 按类标评估
n_classes = len(classes)
class_correct, class_total = [0]*n_classes, [0]* n_classes

with torch.no_grad():
  for images, labels in testloader:
    outputs = net(images)
    _, predicted = torch.max(outputs, 1)
    is_correct = (labels == predicted).squeeze()
    for i in range(len(labels)):
      label = labels[i]
      class_total[label] += 1
      class_correct[label] += is_correct[i].item()

for i in range(n_classes):
  print('Accuracy of %5s: %.2f %%' % (
    classes[i], 100.0 * class_correct[i] / class_total[i]
  ))

Accuracy of plane: 67.00 %
Accuracy of  car: 71.50 %
Accuracy of bird: 55.20 %
Accuracy of  cat: 45.60 %
Accuracy of deer: 38.20 %
Accuracy of  dog: 47.00 %
Accuracy of frog: 78.80 %
Accuracy of horse: 55.90 %
Accuracy of ship: 72.70 %
Accuracy of truck: 57.50 %

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 假设我们在支持CUDA的机器上，我们可以打印出CUDA设备：

print(device)

cuda:0

net.to(device)

Net(
 (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
 (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
 (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
 (fc1): Linear(in_features=400, out_features=120, bias=True)
 (fc2): Linear(in_features=120, out_features=84, bias=True)
 (fc3): Linear(in_features=84, out_features=10, bias=True)
)

inputs, labels = inputs.to(device), labels.to(device)