CIFAR10数据集训练及测试

大家好，欢迎来到IT知识分享网。

一、数据集介绍        

        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。这里面有50000张用于训练，构成了5个训练批，每一批10000张图；另外10000用于测试，单独构成一批。测试批的数据里，取自10类中的每一类，每一类随机取1000张。抽剩下的就随机排列组成了训练批。注意一个训练批中的各类图像并不一定数量相同，总的来看训练批，每一类都有5000张图。

        下面这幅图就是列举了10各类，每一类展示了随机的10张图片：

二、搭建神经网络模型

        使用CIFAR10网路模型，基于pytorch搭建网络模型

import torch
from torch import nn

class Test(nn.Module):
    def __init__(self):
        super(Test, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(1024, 64),
            nn.Linear(64, 10)
        )

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

三、数据集的准备及加载

         使用torchvision.datasets.CIFAR10()加载数据集，train=True表示数据集为训练数据集，train=False表示数据集为测试集，dowwnload=True表示下载数据集，本地存在数据集不会再次下载。

import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
from model import *

# 定义训练设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# 准备数据集
train_data = torchvision.datasets.CIFAR10("dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                         download=True)
test_data = torchvision.datasets.CIFAR10("dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)
# print("训练数据集的长度为{}".format(train_data_size))
# print("测试数据集的长度为{}".format(test_data_size))

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

 四、神经网络、损失函数、优化器等加载

test = Test()
test = test.to(device)

# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(test.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
epoch = 30

# 添加Tensorboard
writer = SummaryWriter("logs_train")

 五、训练、测试、模型保存

start_time = time.time()
for i in range(epoch):
    print("-----第{}轮训练开始------".format(i+1))

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

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数{}, Loss:{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    test.eval()
    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 = test(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
    total_test_step += 1

    torch.save(test, "test_{}.pth".format(i))
    print("模型已保存")

writer.close()

 六、模型的加载及测试

import torch
import torchvision
from PIL import Image
from model import *
CLASS = ["airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck"]
image_path = "./imgs/dog.png"
image = Image.open(image_path)
# print(image)

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

image = transform(image)
# print(image.shape)


model = torch.load("test_99.pth", map_location=torch.device('cpu'))
# print(model)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
    output = model(image)
ret = output.argmax(1)
ret = ret.numpy()
print("预测结果为:{}".format(CLASS[ret[0]]))