基于Pytorch的CIFAR10数据集训练与识别

一、CIFAR10数据集介绍

CIFAR10数据集共有十个类别,分别是airplane、automobile、bird、cat、deer、dog、frog、horse、ship、truck

二、模型训练

模型代码:

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x

gpu训练代码:(使用gpu训练速度很快,几分钟就可以完成,30轮训练完成后,准确率在百分之60多)

import torchvision
from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
import torch
from torch import nn
# 定义训练的设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)

train_data = torchvision.datasets.CIFAR10("./CDataset", train=True,
                                          transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10("./CDataset", train=False,
                                         transform=torchvision.transforms.ToTensor(), download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)

# 利用Dataloader加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
net = Net()
net = net.to(device)
# 创建损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate )

# 设置训练网络的参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练轮数
epoch = 30
for i in range(epoch):
    print("第{}轮训练开始".format(i + 1))

    # 训练步骤开始
    net.train() #可删除
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        output = net(imgs)
        loss = loss_fn(output, targets)

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            print("训练次数:{},Loss:{}".format(total_train_step, loss))

    # 测试步骤开始
    net.eval() #可删除
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = net(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集上的Loss:{}".format(total_test_loss))
    print("整体测试集上的正确率{}".format(total_accuracy / test_data_size))

torch.save(net, "./net.pth")

测试代码:

import torch
import torchvision
from PIL import Image
from torch import nn

# 测试图片的相对路径
image_path = "./image/deer.png"
image = Image.open(image_path)
# 如果是png图片需要转换为3通道的RGB图片
image = image.convert('RGB')

transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize((32, 32)),
    torchvision.transforms.ToTensor()]
)
image = transform(image)


# 采用torch.save()方法保存训练好的模型,这一模型不是pytorch中的,因此需要将模型的代码粘贴在这里
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x


# 模型是在Gpu上训练的,因此这里可以将模型加载到cpu上,也可以使用.cuda()将数据放到gpu上

model = torch.load("net.pth", map_location=torch.device('cpu'))
image = torch.reshape(image, (1, 3, 32, 32))
# image = image.cuda()

model.eval()
with torch.no_grad():
    output = model(image)

Classification = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
# 获取tensor中只有一个值的具体值
type = output.argmax(1)[0].item()
print(Classification[type])

上一篇:图像分类篇:实现pytorch官网demo(LeNet)


下一篇:【无标题】3DCNN在高光谱数据中的运算过程,以nn.Conv3D为例