3.pytorch cifar10-Toy模板网

这篇具有很好参考价值的文章主要介绍了3.pytorch cifar10。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

数据集

CIFAR10 是由 Hinton 的学生 Alex Krizhevsky、Ilya Sutskever 收集的一个用于普适物体识别的计算机视觉数据集，它包含 60000 张 32 X 32 的 RGB 彩色图片，总共 10 个分类。
这些类别分别是飞机、汽车、鸟类、猫、鹿、狗、青蛙、马、船和卡车。其中，包括 50000 张用于训练集，10000 张用于测试集。文章来源地址https://www.toymoban.com/news/detail-766121.html

run

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
import time
import os
 
# transform 的作用主要是用来对数据进行预处理。
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(), # 随机翻转图片 , 数据增强
    transforms.RandomGrayscale(), # 随机调整图片的亮度
    transforms.ToTensor(), # 数据集加载时，默认的图片格式是numpy，所以通过transforms转换成 Tensor。然后再对输入图片进行标准化。
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) # 给定均值：(R,G,B) 方差：（R，G，B），将会把Tensor正则化
])
 
transform1 = transforms.Compose([
    transforms.ToTensor(), # 测试的时候，并不需要对数据进行增强
    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=100,
                                          shuffle=True # shuffle = True 表明提取数据时，随机打乱顺序
                                          )
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform1)
testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                         shuffle=False)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')


class Net(nn.Module):
 
 
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = nn.Conv2d(3,64,3,padding=1)
        self.conv2 = nn.Conv2d(64,64,3,padding=1)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu1 = nn.ReLU()
 
        self.conv3 = nn.Conv2d(64,128,3,padding=1)
        self.conv4 = nn.Conv2d(128, 128, 3,padding=1)
        self.pool2 = nn.MaxPool2d(2, 2, padding=1)
        self.bn2 = nn.BatchNorm2d(128)
        self.relu2 = nn.ReLU()
 
        self.conv5 = nn.Conv2d(128,128, 3,padding=1)
        self.conv6 = nn.Conv2d(128, 128, 3,padding=1)
        self.conv7 = nn.Conv2d(128, 128, 1,padding=1)
        self.pool3 = nn.MaxPool2d(2, 2, padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        self.relu3 = nn.ReLU()
 
        self.conv8 = nn.Conv2d(128, 256, 3,padding=1)
        self.conv9 = nn.Conv2d(256, 256, 3, padding=1)
        self.conv10 = nn.Conv2d(256, 256, 1, padding=1)
        self.pool4 = nn.MaxPool2d(2, 2, padding=1)
        self.bn4 = nn.BatchNorm2d(256)
        self.relu4 = nn.ReLU()
 
        self.conv11 = nn.Conv2d(256, 512, 3, padding=1)
        self.conv12 = nn.Conv2d(512, 512, 3, padding=1)
        self.conv13 = nn.Conv2d(512, 512, 1, padding=1)
        self.pool5 = nn.MaxPool2d(2, 2, padding=1)
        self.bn5 = nn.BatchNorm2d(512)
        self.relu5 = nn.ReLU()
 
        self.fc14 = nn.Linear(512*4*4,1024)
        self.drop1 = nn.Dropout2d()
        self.fc15 = nn.Linear(1024,1024)
        self.drop2 = nn.Dropout2d()
        self.fc16 = nn.Linear(1024,10)
 
 
    def forward(self,x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.pool1(x)
        x = self.bn1(x)
        x = self.relu1(x)
 
 
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.pool2(x)
        x = self.bn2(x)
        x = self.relu2(x)
 
        x = self.conv5(x)
        x = self.conv6(x)
        x = self.conv7(x)
        x = self.pool3(x)
        x = self.bn3(x)
        x = self.relu3(x)
 
        x = self.conv8(x)
        x = self.conv9(x)
        x = self.conv10(x)
        x = self.pool4(x)
        x = self.bn4(x)
        x = self.relu4(x)
 
        x = self.conv11(x)
        x = self.conv12(x)
        x = self.conv13(x)
        x = self.pool5(x)
        x = self.bn5(x)
        x = self.relu5(x)
        # print(" x shape ",x.size())
        x = x.view(-1,512*4*4)
        x = F.relu(self.fc14(x))
        x = self.drop1(x)
        x = F.relu(self.fc15(x))
        x = self.drop2(x)
        x = self.fc16(x)
 
        return x
 
    def train_sgd(self,device):
        optimizer = optim.Adam(self.parameters(), lr=0.0001)
 
        path = 'weights.tar'
        initepoch = 0
 
        if os.path.exists(path) is not True:
            loss = nn.CrossEntropyLoss()
            # optimizer = optim.SGD(self.parameters(),lr=0.01)
 
        else:
            checkpoint = torch.load(path)
            self.load_state_dict(checkpoint['model_state_dict'])
            optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
            initepoch = checkpoint['epoch']
            loss = checkpoint['loss']
 
        for epoch in range(initepoch,100):  # loop over the dataset multiple times
            timestart = time.time()
 
            running_loss = 0.0
            total = 0
            correct = 0
            for i, data in enumerate(trainloader, 0):
                # get the inputs
                inputs, labels = data
                inputs, labels = inputs.to(device),labels.to(device)
 
                # zero the parameter gradients
                optimizer.zero_grad()
 
                # forward + backward + optimize
                outputs = self(inputs)
                l = loss(outputs, labels)
                l.backward()
                optimizer.step()
 
                # print statistics
                running_loss += l.item()
                # print("i ",i)
                if i % 500 == 499:  # print every 500 mini-batches
                    print('[%d, %5d] loss: %.4f' %
                          (epoch, i, running_loss / 500))
                    running_loss = 0.0
                    _, predicted = torch.max(outputs.data, 1)
                    total += labels.size(0)
                    correct += (predicted == labels).sum().item()
                    print('Accuracy of the network on the %d tran images: %.3f %%' % (total,
                            100.0 * correct / total))
                    total = 0
                    correct = 0
                    torch.save({'epoch':epoch,
                                'model_state_dict':net.state_dict(),
                                'optimizer_state_dict':optimizer.state_dict(),
                                'loss':loss
                                },path)
 
            print('epoch %d cost %3f sec' %(epoch,time.time()-timestart))
 
        print('Finished Training')
 
    def test(self,device):
        correct = 0
        total = 0
        with torch.no_grad():
            for data in testloader:
                images, labels = data
                images, labels = images.to(device), labels.to(device)
                outputs = self(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: %.3f %%' % (
                100.0 * correct / total))
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = Net()
net = net.to(device)
net.train_sgd(device)
net.test(device)