这个还是官网 tutorial上的一个例子，还是非常有意思的，感觉搭建网络不用一开始就上大数据集，可以先用小数据集进行简单训练和inference，为啥呢？
如果上来一个大数据集，每次调试载入数据都得30分钟，然后发现存在一个小问题，还不如用个小数据集，确认无误了，再用大数据集，包括预处理也是，先用一部分数据测试可行性，不然时间成本太高了。。。
#载入对应依赖库 import torch import torchvision import torchvision.transforms as transforms #官网上说数据集的输出为[0,1]的范围 #要将其的转化为范围为[-1, 1] #因为输入数据是3个通道的，所以设置每个通道的mean为（0.5,0.5,0.5）， # standard deviations为（0.5，0.5,0.5） transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) #这边建议download=False,自己到网站上去下载对应的数据到./data目录下，不然的话会很久 #有种错觉是不是代码写错了。。。 trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform = transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers = 0) testset = torchvision.datasets.CIFAR10(root='./data', train= False, download=False, 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') #显示一些图片 import matplotlib.pyplot as plt import numpy as np def imshow(img): img = img /2 + 0.5 npimg = img.numpy() plt.imshow(np.transpose(npimg, (1, 2, 0))) plt.show() dataiter = iter(trainloader) images, labels = dataiter.next() imshow(torchvision.utils.make_grid(images)) print(' '.join('%5s' %classes[labels[j]] for j in range(4))) deer truck dog cat #开始构建自己的网络 import torch 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, 3) 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() print(net) Net( (conv1): Conv2d(3, 6, kernel_size=(3, 3), 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) ) #设置交叉熵作为损失函数，不清楚的可以看cs231n的课程 import torch.optim as optim criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) #设置epoch为2，也就是整个数据学习两轮 for epoch in range(2): running_loss = 0.0 for i, data in enumerate(trainloader, 0): inputs, labels = data optimizer.zero_grad() outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() running_loss += loss.item() if i % 2000 == 1999: print('[%d, %5d] loss: %.3f' %(epoch+1, i+1, running_loss/2000)) running_loss = 0.0 print('Finished Training') [1, 2000] loss: 1.229 [1, 4000] loss: 1.234 [1, 6000] loss: 1.210 [1, 8000] loss: 1.219 [1, 10000] loss: 1.206 [1, 12000] loss: 1.209 [2, 2000] loss: 1.134 [2, 4000] loss: 1.145 [2, 6000] loss: 1.136 [2, 8000] loss: 1.119 [2, 10000] loss: 1.138 [2, 12000] loss: 1.117 Finished Training #保存模型 PATH = './cifar_net.pth' torch.save(net.state_dict(), PATH) #显示部分测试的图片 dataiter = iter(testloader) images, labels = dataiter.next() imshow(torchvision.utils.make_grid(images)) print('GroundTruth: ', ' '.join('%5s'%classes[labels[j]] for j in range(4))) GroundTruth: cat ship ship plane #重新加载模型 net = Net() net.load_state_dict(torch.load(PATH)) IncompatibleKeys(missing_keys=[], unexpected_keys=[]) #预测一下，好像对了50%。。。。 _, predicted = torch.max(outputs, 1) print('Predicted: ', ' '.join('%5s'% classes[predicted[j]] for j in range(4))) Predicted: frog ship car plane #测试总的准确率 correct = 0 total = 0 with torch.no_grad(): for data in testloader: images, labels = data outputs = net(images) #输出可能性最大的index _, predicted = torch.max(outputs.data, 1) total += labels.size(0) #计算label和predicted相同的个数总和，就是预测对的数量 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: 57 % #查看具体每一类的准确率 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])) 猫和狗学的好差。。。。 Accuracy of plane : 80 % Accuracy of car : 79 % Accuracy of bird : 37 % Accuracy of cat : 33 % Accuracy of deer : 44 % Accuracy of dog : 39 % Accuracy of frog : 63 % Accuracy of horse : 58 % Accuracy of ship : 76 % Accuracy of truck : 60 % #如果有GPU，当然使用GPU啦，不然好浪费，感觉LZ的970m小笔记本都快被榨干了。。。 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(device) cuda:0 #将网络和数据从CPU上移到GPU上去 net.to(device) inputs, labels = data[0].to(device), data[1].to(device)感觉基本的操作都进行了一遍，后续还要继续学习O(∩_∩)O哈哈~
参考地址： https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py
