CIFAR分类

import torchvision as tv
import torchvision.transforms as transforms
from torch import optim
import torch as t
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F# 准备数据集
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# 训练数据集有5w
trainset = tv.datasets.CIFAR10(root="/home/cy/data",train=True,download=True,transform=transform
)trainloader = t.utils.data.DataLoader(trainset,batch_size=4,shuffle=True,num_workers=0
)
# 测试数据有1w
testset = tv.datasets.CIFAR10("/home/cy/data",train=False,download=True,transform=transform
)testloader = t.utils.data.DataLoader(testset,batch_size=4,shuffle=False,num_workers=0
)
# 一共有10个种类
#classes = ("plane", "car", "bird", "cat", "deer", "dog", "forg", "horse", "ship", "truck")
# 迭代
dataiter = iter(trainloader)
images, labels = dataiter.next()# 模型
class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(3, 6, 5)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 = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))x = F.max_pool2d(F.relu(self.conv2(x)), 2)x = x.view(x.size()[0], -1)x = F.relu(self.fc1(x))x = F.relu(self.fc2(x))x = self.fc3(x)return xdef train():net = Net()# 损失函数和优化器criterion = nn.CrossEntropyLoss()optimzer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)# 训练网络for epoch in range(10):running_loss = 0.0for i, data in enumerate(trainloader, 0):# 输入数据inputs, labels = datainputs, labels = Variable(inputs), Variable(labels)# 梯度清零optimzer.zero_grad()# forward + backwardoutputs = net(inputs)loss = criterion(outputs, labels)loss.backward()# 更新参数optimzer.step()# 打印log信息print(loss.item())running_loss += loss.item()print()if i % 2000 == 1999:print("训练结果：[%d, %5d] loss: %.3f" % (epoch + 1, i + 1, running_loss / 2000))running_loss = 0.0print("Finish Training")# 测试训练结果correct = 0total = 0for data in testloader:images, labels = dataoutputs = net(Variable(images))total += len(labels)_, predicted = t.max(outputs.data, 1)correct += (predicted == labels).sum()print("10000张图片中预测的准确率为：%d %%"%(100*correct/total))train()

运行部分结果