CIFAR10彩色图片识别

 🍨 本文为365天深度学习训练营 中的学习记录博客

 🍖 原作者：K同学啊

我的环境

python 3.9

使用jupyter

torch==1.13.0+cu116

torchvision==0.14.0+cu116

运行代码

import warnings

import numpy as np
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
import os

from torchinfo import summary

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"


device = torch.device("cuda"if torch.cuda.is_available() else "cpu")

print(device)

 

# 划分数据集
train_ds = torchvision.datasets.CIFAR10('re/data',train=True,
                                        transform=torchvision.transforms.ToTensor(),
                                        download=True)
test_ds = torchvision.datasets.CIFAR10('re/data',train=False,
                                       transform=torchvision.transforms.ToTensor(),
                                       download=True)
#数据加载
batch_size = 32
train_loader = torch.utils.data.DataLoader(train_ds,
                                           batch_size=batch_size
                                           ,shuffle=True)
test_loader = torch.utils.data.DataLoader(test_ds,
                                          batch_size=batch_size)# shuffle:重新排列数据

# 取一个批次查看数据格式
imgs,labels = next(iter(train_loader))
print(imgs.shape)  # shape:[batch_size,channel,height,weight]

# 数据可视化
plt.figure(figsize=(20,5))
for i,imgs in enumerate(imgs[:20]):
    npimg = imgs.numpy().transpose((1,2,0))
    #将tensor变成numpy，图像数据从 (channels, height, width) 格式转换为 (height, width, channels) 格式，
    plt.subplot(2,10,i+1)
    plt.imshow(npimg,cmap=plt.cm.binary)
    plt.axis('off')
plt.show()

 # 构建网络
num_classes = 10 #图片类别数
class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.module1 = nn.Sequential(
            #卷积+池化
            nn.Conv2d(3,64,3,1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(64,64,3,1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(64, 128, 3, 1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            #全连接
            nn.Flatten(start_dim=1),
            nn.Linear(512,256),
            nn.ReLU(),
            nn.Linear(256,num_classes)
        )
    #前向传播
    def forward(self,x):
        x = self.module1(x)
        return x

#打印加载模型
model = Model().to(device) # 到GPU中运行

summary(model)

# 模型训练
loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-2
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
#训练函数
def train(dataloader,model,loss_fn,optimizer):
    size = len(dataloader.dataset) # 训练集大小
    num_batches = len(dataloader)  # 训练批次数目
    train_loss,train_acc = 0,0
    for X,y in dataloader:
        X,y = X.to(device),y.to(device)

        # 计算预测误差
        pred = model(X)
        loss = loss_fn(pred,y)

        #反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 计算acc，loss
        train_acc = train_acc + y.eq(pred.argmax(dim=1)).type(torch.float).sum().item() #对的个数
        train_loss = train_loss + loss.item()

    train_acc = train_acc/size
    train_loss = train_loss/num_batches
    return train_acc,train_loss
# 测试函数
def test(dataloader,model,loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss,test_acc = 0,0

    with torch.no_grad():
        for imgs,target in dataloader:
            imgs,target = imgs.to(device),target.to(device)
            # 计算loss
            target_pred = model(imgs)
            loss= loss_fn(target_pred,target)

            test_loss += loss.item()
            # 计算acc
            test_acc += target.eq(target_pred.argmax(1)).type(torch.float).sum().item()

        test_acc /= size
        test_loss /= num_batches
        return test_acc,test_loss

# 正式训练
epochs = 10
train_loss = []
train_acc = []
test_loss = []
test_acc = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc,epoch_train_loss = train(train_loader,model,loss_fn,opt)

    model.eval()
    epoch_test_acc,epoch_test_loss = test(test_loader,model,loss_fn)

    train_loss.append(epoch_train_loss)
    train_acc.append(epoch_train_acc)
    test_loss.append(epoch_test_loss)
    test_acc.append(epoch_test_acc)

    template = ('Epoch:{:2d},Train_acc:{:.1f}%,Train_loss:{:.3f},Test_acc:{:.1f}%,Test_loss:{:.3f}')
    print(template.format(epoch+1,epoch_train_acc*100,epoch_train_loss,epoch_test_acc*100,epoch_test_loss))

 # 可视化
warnings.filterwarnings('ignore')
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100  # 分辨率

epochs_range = range(1,epochs+1)

plt.figure(figsize=(12,3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range,train_acc,label='Train_acc')
plt.plot(epochs_range,test_acc,label='Test_acc')
plt.legend(loc='lower right')
plt.title('Training and Test Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range,train_loss,label='Train_loss')
plt.plot(epochs_range,test_loss,label='Test_loss')
plt.legend(loc='upper right')
plt.title('Training and Test Loss')
plt.show()
print(train_loss,train_acc)
print(test_loss,test_acc)

学习总结

CIFAR-10是一个流行的计算机视觉数据集，主要用于图像识别和分类任务的训练和测试。这个数据集包含了60000张32x32像素的彩色图像，这些图像被分为10个类别，每个类别6000张图像。这些类别包括飞机、汽车、鸟、猫、鹿、狗、青蛙、马、船和卡车。在对CIFAR-10数据集训练时，首先需要对数据进行预处理，使用交叉熵损失函数，使用SGD优化器来最小化损失函数。主要学会了构建CNN网络，学习推导卷积层与池化层的计算过程。