第P2周：Pytorch实现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

目标

实现CIFAR-10的彩色图片识别
实现比P1周更复杂一点的CNN网络

具体实现

（一）环境

语言环境：Python 3.10
编译器: PyCharm
框架: Pytorch 2.5.1

（二）具体步骤

1.

import torch  
import torch.nn as nn  
import matplotlib.pyplot as plt  
import torchvision  # 第一步：设置GPU  
def USE_GPU():  if torch.cuda.is_available():  print('CUDA is available, will use GPU')  device = torch.device("cuda")  else:  print('CUDA is not available. Will use CPU')  device = torch.device("cpu")  return device  device = USE_GPU()

输出：CUDA is available, will use GPU

  
# 第二步：导入数据。同样的CIFAR-10也是torch内置了，可以自动下载  
train_dataset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True,  transform=torchvision.transforms.ToTensor())  
test_dataset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True,  transform=torchvision.transforms.ToTensor())  batch_size = 32  
train_dataload = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)  
test_dataload = torch.utils.data.DataLoader(test_dataset, 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为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。  
imgs, labels = next(iter(train_dataload))  
print(imgs.shape)  # 查看一下图片  
import numpy as np  
plt.figure(figsize=(20, 5))  
for i, images in enumerate(imgs[:20]):  # 使用numpy的transpose将张量（C,H, W)转换成（H, W, C)，便于可视化处理  npimg = imgs.numpy().transpose((1, 2, 0))  # 将整个figure分成2行10列，并绘制第i+1个子图  plt.subplot(2, 10, i+1)  plt.imshow(npimg, cmap=plt.cm.binary)  plt.axis('off')  
plt.show()

输出：
Files already downloaded and verified
Files already downloaded and verified
torch.Size([32, 3, 32, 32])

# 第三步，构建CNN网络  
import torch.nn.functional as F  num_classes = 10  # 因为CIFAR-10是10种类型  
class Model(nn.Module):  def __init__(self):  super(Model, self).__init__()  # 提取特征网络  self.conv1 = nn.Conv2d(3, 64, 3)  self.pool1 = nn.MaxPool2d(kernel_size=2)  self.conv2 = nn.Conv2d(64, 64, 3)  self.pool2 = nn.MaxPool2d(kernel_size=2)  self.conv3 = nn.Conv2d(64, 128, 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, 1)  x = F.relu(self.fc1(x))  x = self.fc2(x)  return x  from torchinfo import summary  
# 将模型转移到GPU中  
model = Model().to(device)  
summary(model)

# 训练模型  
loss_fn = nn.CrossEntropyLoss() # 创建损失函数  
learn_rate = 1e-2   # 设置学习率  
opt = torch.optim.SGD(model.parameters(), lr=learn_rate)    # 设置优化器  # 编写训练函数  
def train(dataloader, model, loss_fn, optimizer):  size = len(dataloader.dataset) # 训练集的大小 ，这里一共是60000张图片  num_batches = len(dataloader)   # 批次大小，这里是1875（60000/32=1875)  train_acc, train_loss = 0, 0    # 初始化训练正确率和损失率都为0  for X, y in dataloader: # 获取图片及标签，X-图片，y-标签（也是实际值）  X, y = X.to(device), y.to(device)  # 计算预测误差  pred = model(X) # 网络输出预测值  loss = loss_fn(pred, y) # 计算网络输出的预测值和实际值之间的差距  # 反向传播  optimizer.zero_grad()   # grad属性归零  loss.backward() # 反向传播  optimizer.step()    # 第一步自动更新  # 记录正确率和损失率  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  # 测试函数  
def test(dataloader, model, loss_fn):  size = len(dataloader.dataset) # 测试集大小，这里一共是10000张图片  num_batches = len(dataloader)   # 批次大小 ，这里312，即10000/32=312.5,向上取整  test_acc, test_loss = 0, 0  # 因为是测试，因此不用训练，梯度也不用计算不用更新  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()  test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()  test_acc /= size  test_loss /= num_batches  return test_acc, test_loss  # 正式训练  
epochs = 10  
train_acc, train_loss, test_acc, test_loss = [], [], [], []  for epoch in range(epochs):  model.train()  epoch_train_acc, epoch_train_loss = train(train_dataload, model, loss_fn, opt)  model.eval()  epoch_test_acc, epoch_test_loss = test(test_dataload, 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}, 训练正确率:{:.1f}%, 训练损失率:{:.3f}, 测试正确率：{:.1f}%, 测试损失率：{:.3f}'  print(template.format(epoch+1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))  print('Done')  # 结果可视化  
# 隐藏警告  
import warnings  
warnings.filterwarnings('ignore')   # 忽略警告信息  
plt.rcParams['font.sans-serif'] = ['SimHei']    # 正常显示中文标签  
plt.rcParams['axes.unicode_minus'] = False  # 正常显示+/-号  
plt.rcParams['figure.dpi'] = 100    # 分辨率  epochs_range = range(epochs)  plt.figure(figsize=(12, 3))  plt.subplot(1, 2, 1)    # 第一张子图  
plt.plot(epochs_range, train_acc, label='训练正确率')  
plt.plot(epochs_range, test_acc, label='测试正确率')  
plt.legend(loc='lower right')  
plt.title('训练和测试正确率比较')  plt.subplot(1, 2, 2)    # 第二张子图  
plt.plot(epochs_range, train_loss, label='训练损失率')  
plt.plot(epochs_range, test_loss, label='测试损失率')  
plt.legend(loc='upper right')  
plt.title('训练和测试损失率比较')  plt.show()# 保存模型  
torch.save(model, './models/cnn-cifar10.pth')

再次设置epochs为50训练结果：

epochs增加到100，训练结果：

可以看到训练集和测试集的差距有点大，不太理想。做一下数据增加试试：

data_transforms= {  'train': transforms.Compose([  transforms.RandomHorizontalFlip(),  transforms.ToTensor(),  ]),  'test': transforms.Compose([  transforms.ToTensor(),  ])  
}

在dataset中：

train_dataset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True,  transform=data_transforms['train'])  
test_dataset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=data_transforms['test'])

运行结果：

比较漂亮了，再调整batch_size=16和epochs=20,提高了近6个百分点。

batch_size=16,epochs=50:有第20轮左右的时候，验证集的确认性基本就没有再提高了。和上面基本一样。