训练一个分类器
我们已经知道了：
- 如何定义一个模型: torch.nn
- 如何计算损失: loss = nn.CrossEntropyLoss()
- 如何更新参数: optimizer = nn.optim.SGD(net.parameters(), lr = 0.0001, momentum=0.9)
关于数据
一般来说，当你需要去处理 image、text、audio 或者 video数据的时候，可以通过Python包加载这些数据，转化为numpy类型的数据。然后将numpy类型的数据转化为 torch.***Tensor。
- 对于图像，常用的有：Pillow，OpenCV
- 对于语音，常用的有：scipy, libosa
- 对于文本，常用的有：NLTK, SpaCy
Pytorch提供了处理图像数据的工具包 torchvision，提供了常见数据集(Imagenet, CIFAR10, MNIST)的数据加载函数，以及数据转化函数，封装在 torchvision.datasets 和torch.utils.data.DataLoader之中。
这为我们提供了很大的便利性，同时避免了重复写重复的代码。
使用CIFAR10数据集，图片数据包含以下类别：‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’。图片尺寸为 (3,32,32)。
image.png
训练一个图片分类器
1、加载并处理CIFAR10数据
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')
# 输出
Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz
Extracting ./data/cifar-10-python.tar.gz to ./data
Files already downloaded and verified
显示几张图片
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
显示
horse frog horse bird
2、定义卷积神经网络
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()
3、定义损失函数和优化器
import torch.optim as optim
criterion = nn.CrossEntropyLoss() # 多分类器交叉熵损失函数 包含了
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) # SGD梯度下降
4、训练神经网络
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
# 输出
[1, 2000] loss: 2.229
[1, 4000] loss: 1.877
[1, 6000] loss: 1.678
[1, 8000] loss: 1.576
[1, 10000] loss: 1.502
[1, 12000] loss: 1.476
[2, 2000] loss: 1.381
[2, 4000] loss: 1.370
[2, 6000] loss: 1.344
[2, 8000] loss: 1.326
[2, 10000] loss: 1.324
[2, 12000] loss: 1.294
Finished Training
- 快速保存模型
PATH = './cifar_net.p'
torch.save(net.state_dict(), PATH)
5、在测试集上测试网络
让我们看看分类模型是否有效
输出GroundTruth
dataiter = iter(testloader)
images, labels = dataiter.next()
# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
image.png
- 加载模型
net = Net()
net.load_state_dict(torch.load(PATH))
模型加载完成，看看模型是否有效
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))
结果看起来很不错
看看在整个数据集上表现如何
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))
# 输出
Accuracy of the network on the 10000 test images: 54 %
考虑到我们一个有10类，随记猜测的准确率在10% ，目前54%的准确LV看起来确实很不错，我们的神经网络学到了一些特征。
我们看看不同的类别的准确率，也可以使用sklearn的混淆矩阵，来评估效果。
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]))
# 输出
Accuracy of plane : 66 %
Accuracy of car : 61 %
Accuracy of bird : 27 %
Accuracy of cat : 24 %
Accuracy of deer : 51 %
Accuracy of dog : 41 %
Accuracy of frog : 70 %
Accuracy of horse : 65 %
Accuracy of ship : 61 %
Accuracy of truck : 70 %
目前我们已经构造了一个分类器，那么接下来我们需要干什么呢？
尝试使用GPU进行处理。
6、在GPU上进行训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Assuming that we are on a CUDA machine, this should print a CUDA device:
print(device)
然后将模型参数和训练数据转化为CUDA tensors
# 模型参数转化为CUDA Tensor
net.to(device)
# 将数据转化为CUDA tensors
inputs, labels = data[0].to(device), data[1].to(device)
