CIFAR10彩色图片识别

>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

编译器：colab

一：前期准备

1.设置GPU

如果设备上支持GPU就使用GPU,否则使用CPU

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision

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

2.导入数据

使用dataloader加载数据，并设置好基本的batch_size

train_ds = torchvision.datasets.CIFAR10('data',train = True,transform = torchvision.transforms.ToTensor(),download=True)
test_ds = torchvision.datasets.CIFAR10('data',train=False,transform=torchvision.transforms.ToTensor(),download=True)

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds, 
                                       batch_size=batch_size, 
                                       shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds, 
                                       batch_size=batch_size)

#取一个批次查看数据格式
#数据的shape为:[batch_size,channel,height,weight]
#其中batch_size为自己的设定，channel, height,weight分别是图片的通道数，高度和宽度
images,labels = next(iter(train_dl))
images.shape

3.数据可视化

import numpy as np

 # 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5)) 
for i, imgs in enumerate(imgs[:20]):
    # 维度缩减
    npimg = imgs.numpy().transpose((1, 2, 0))#将张量转换为numpy数组并调整通道顺序
    # 将整个figure分成2行10列，绘制第i+1个子图。
    plt.subplot(2, 10, i+1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')
    
#plt.show()  如果你使用的是Pycharm编译器，请加上这行代码

二：构建简单的CNN网络

import torch.nn.functional as F

num_classes = 10  # 图片的类别数

class Model(nn.Module):
     def __init__(self):
        super().__init__()
         # 特征提取网络
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3)   # 第一层卷积,卷积核大小为3*3
        self.pool1 = nn.MaxPool2d(kernel_size=2)       # 设置池化层，池化核大小为2*2
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3)  # 第二层卷积,卷积核大小为3*3   
        self.pool2 = nn.MaxPool2d(kernel_size=2) 
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3) # 第二层卷积,卷积核大小为3*3   
        self.pool3 = nn.MaxPool2d(kernel_size=2) 
                                      
        # 分类网络
        self.fc1 = nn.Linear(512, 256)          
        self.fc2 = nn.Linear(256, num_classes)
     # 前向传播
     def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))     
        x = self.pool2(F.relu(self.conv2(x)))
        x = self.pool3(F.relu(self.conv3(x)))
        
        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)
       
        return x

网络结构图：

加载并打印模型

from torchinfo import summary
model = Model().to(device)
summary(model)

三：训练模型

1.设置超参数

loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-2 
opt = torch.optim.SGD(model.parameters(),lr = learn_rate)

2.编写训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  
    num_batches = len(dataloader)  

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率
    
    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)
        
        # 计算预测误差
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
        
        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        
        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

3.编写测试函数

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)
      target_pred= model(imgs)
      loss =loss_fn(target_pred,target)

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

  test_acc /= size
  test_loss /= num_batches

  return test_acc, test_loss

4.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_dl, model, loss_fn, opt)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    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))
print('Done')

四：结果可视化

import matplotlib.pyplot as plt
import warnings
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(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

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

五：总结

通过彩色图片识别的案例，学习了如何通过DataLoader加载和处理数据，并且初步认识了如何构建简单的cnn网络，如何训练模型，从最后的训练结果可知，模型的拟合效果较好。