1 数据来源是什么?
一般图像领域分类问题公共数据集有ImagetNet,CIFRA10,CIFRA100,MINIST数据集,这里简单介绍一下
- ImageNet Imagenet数据集是目前深度学习图像领域应用得非常多的一个领域,关于图像分类、定位、检测等研究工作大多基于此数据集展开。而且文档详细,有专门的团队维护,使用非常方便,在计算机视觉领域研究论文中应用非常广,几乎成为了目前深度学习图像领域算法性能检验的“标准”数据集。Imagenet数据集有1400多万幅图片,涵盖2万多个类别。
- CIFRA10 该数据集共有60000张彩色图像,这些图像是32*32,分为10个类,每类6000张图。
- CIFRA100 此数据集与CIFAR-10类似,不同之处在于它有100个类,每个类包含600个图像。每类分为500个训练图像和100个测试图像。其中100个类分为20个大类。每个图像都带有一个“精细”标签(它所属的类)和一个“粗略”标签(它所属的大类)。
- MNIST MNIST 数据集来自美国国家标准与技术研究所, National Institute of Standards and Technology (NIST). 训练集 (training set) 由来自 250 个不同人手写的数字构成, 其中 50% 是高中学生, 50% 来自人口普查局 (the Census Bureau) 的工作人员. 测试集(test set) 也是同样比例的手写数字数据.
这里我们采用CIFRA10数据集
2 怎么导入数据
方法一
使用opencv,pillow将图像导入成numpy的array,再转tensor
方法二
使用tourch的包torchvision
3 训练步骤
- 使用torchvision导入数据
transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5)) #mean std是一种计算,计算方法是data - mean / std ]) trainset = torchvision.datasets.CIFAR10( root='./data',train=True,download=True,transform=transform ) #trainLoader对trainSet进行操作的工具,shuffle操作代表每次取出batch以后重新洗牌 trainLoader = torch.utils.data.DataLoader( trainset,batch_size=4,shuffle=True,num_workers=0 ) 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=0) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
- 定义一个神经网络
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
- 定义损失函数和优化器
##定义损失函数和优化器 net = Net() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(),lr=0.001,momentum=0.9)
- 训练神经网络
for epoch in range(2): runningLoss = 0.0 for i,data in enumerate(trainLoader,0): #enumerate 给可遍历对象赋予索引 inputs,labels = data optimizer.zero_grad() outputs = net(inputs) loss = criterion(outputs,labels) loss.backward() optimizer.step() runningLoss += loss.item() if i%2000 == 1999: print('[%d , %d] loss: %0.3f' % (epoch+1,i+1,runningLoss/2000)) runningLoss = 0.0 print("train finished")
- 测试训练结果
# 对一个batch进行测试****************************************************************************************************************
# 这段代码用于展示图片
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1,2,0)))
plt.show()
# 使用迭代器获取图片
dataiter = iter(trainLoader)
images, labels = dataiter.next()
# 因为得到的是一个batch的图片张量,所以拼成一个图片
imshow(torchvision.utils.make_grid(images))
# %.ns代表打印__str__之后的结果,结果截取n位
print(' '.join('%.5s' % classes[labels[j]] for j in range(4)))
net = Net()
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))
# 对于所有的测试集进行测试******************************************************************************************************
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))
## 测试每个类分别的正确率********************************************************************************************
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]))
4 如何放在GPU上进行计算
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
#将神经网络放在device上
net.to(device)
#将数据放在device上
inputs,labels = data[0].to(device),data[1].to(device)
5 完整代码
#coding=utf-8
import torch
import torchvision
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
#导入数据***************************************************************************************************
#变换的组合,这里面是转成tensor 同时从(0,255)转为(0,1),然后归一化到(-1,1)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5)) #mean std是一种计算,计算方法是data - mean / std
])
trainset = torchvision.datasets.CIFAR10(
root='./data',train=True,download=True,transform=transform
)
#trainLoader对trainSet进行操作的工具,shuffle操作代表每次取出batch以后重新洗牌
trainLoader = torch.utils.data.DataLoader(
trainset,batch_size=4,shuffle=True,num_workers=0
)
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=0)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
#定义网络 ******************************************************************************************************
#Conv2d的参数 [input_channels_number,output_channedls_output,height,width]
#nn.Linear参数 [input_features,output_features]
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
##定义损失函数和优化器
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(),lr=0.001,momentum=0.9)
#训练网络 ******************************************************************************************
for epoch in range(2):
runningLoss = 0.0
for i,data in enumerate(trainLoader,0): #enumerate 给可遍历对象赋予索引
inputs,labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs,labels)
loss.backward()
optimizer.step()
runningLoss += loss.item()
if i%2000 == 1999:
print('[%d , %d] loss: %0.3f' % (epoch+1,i+1,runningLoss/2000))
runningLoss = 0.0
print("train finished")
# 存输模型***********************************************************************************************************************
PATH = './cifar_net.pth'
torch.save(net.state_dict(),PATH)
# 对一个batch进行测试****************************************************************************************************************
# 这段代码用于展示图片
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1,2,0)))
plt.show()
# 使用迭代器获取图片
dataiter = iter(trainLoader)
images, labels = dataiter.next()
# 因为得到的是一个batch的图片张量,所以拼成一个图片
imshow(torchvision.utils.make_grid(images))
# %.ns代表打印__str__之后的结果,结果截取n位
print(' '.join('%.5s' % classes[labels[j]] for j in range(4)))
net = Net()
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))
# 对于所有的测试集进行测试******************************************************************************************************
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))
## 测试每个类分别的正确率********************************************************************************************
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]))