%matplotlib inline
一般情况下处理图像、文本、音频、视频时,可以用标准的python包加载数据到一个numpy
数组中,然后将数组转换为torch.Tensor。
特别的,对于图像任务,使用torchvision包处理一下基本图像数据集。如使用torchvision处理CIFAR10数据集(3x32x32)。
流程如下:
# 使用torchvision加载CIFAR10
import torch
import torchvision
import torchvision.transforms as transforms
# torchvision输出是[0,1]的PIL图像,我们将其转换为[-1,1]的张量
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=2)
testset = torchvision.datasets.CIFAR10(root='./data',train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
Files already downloaded and verified
Files already downloaded and verified
import matplotlib.pyplot as plt
import numpy as np
# 展示图像的函数
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
# 获取随机数据
dataiter = iter(trainloader)
images, labels = dataiter.next()
# 展示图像
imshow(torchvision.utils.make_grid(images))
# 显示图像标签
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
plane deer deer horse
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()
# 使用交叉熵作为损失函数,及带动量的随机梯度下降
import torch.optim as optim
loss_func = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
# 在数据迭代器上循环,将数据输入至网络并优化
for epoch in range(2): # 多批次循环
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# 获取输入
inputs, labels = data
# 梯度清零
optimizer.zero_grad()
# 正向传播,反向传播,优化
outputs = net(inputs)
loss = loss_func(outputs, labels)
loss.backward()
optimizer.step()
# 打印状态信息
running_loss += loss.item()
if i % 2000 == 1999: # 每2000批次打印1次
print('[%d, %5d] loss: %.3f' %
(epoch+1, i+1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
[1, 2000] loss: 2.089
[1, 4000] loss: 1.969
[1, 6000] loss: 1.928
[1, 8000] loss: 1.949
[1, 10000] loss: 1.954
[1, 12000] loss: 1.999
[2, 2000] loss: 1.963
[2, 4000] loss: 2.005
[2, 6000] loss: 2.002
[2, 8000] loss: 1.996
[2, 10000] loss: 2.000
[2, 12000] loss: 1.992
Finished Training
通过预测神经网络输出的类别标签和实际标签进行对比来检测网络的性能,
如果预测正确,我们把该样本添加到正确预测列表。
第一步,显示测试集图片并熟悉图片内容
dataiter = iter(testloader)
images, labels = dataiter.next()
# 显示图片
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]]
for j in range(4)))
GroundTruth: cat ship ship plane
# 神经网络的预测
# 网络的输出是10个标签的能量,能量越大,网络认为是该标签的概率越大。
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))
Predicted: car car ship car
# 在整个测试集上的结果
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).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: 21 %
# 查看每个类的识别精度
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(10):
print("Accuracy of %5s : %2d %%" % (
classes[i], 100 * class_correct[i] / class_total[i]))
Accuracy of plane : 12 %
Accuracy of car : 71 %
Accuracy of bird : 45 %
Accuracy of cat : 13 %
Accuracy of deer : 2 %
Accuracy of dog : 6 %
Accuracy of frog : 28 %
Accuracy of horse : 10 %
Accuracy of ship : 26 %
Accuracy of truck : 0 %
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 显示CUDA信息
print(device)
cpu
# 将递归遍历所有模块并将模块的参数和缓存区转换成CUDA张量:
net.to(device)
# inputs, targets和images也要转换
inputs, labels = inputs.to(device), labels.to(device)