P2 Pytorch入门实战——CIFAR10彩色图片识别

一、前期准备

1. 设置device

# import the necessary libraries
import torch 
import torch.nn as nn
import torch.nn.functional as F
from torchinfo import summary
import torchvision
import numpy as np
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
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
 
# 设置硬件设备,如果有GPU则使用,没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2. 导入数据 

使用dataset下载CIFAR10数据集,并划分好训练集与测试集

# load the data
train_ds = torchvision.datasets.CIFAR10('data', 
                                      train=True, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

test_ds  = torchvision.datasets.CIFAR10('data', 
                                      train=False, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

print('Number of training examples: ', len(train_ds))
print('Number of testing examples: ', len(test_ds))

使用dataloader加载数据,并设置好基本的batch_size

# Data loader
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为自己设定,channel,height和weight分别是图片的通道数,高度和宽度。
"""
The iter() function is used to get an iterator from the data loader (train_dl).
An iterator is an object that allows you to loop through a container (in this case, the data loader) one element at a time.

next() retrieves the next item from the iterator, which, in this context, is the next batch of data from the data loader.
"""
imgs, labels = next(iter(train_dl))
imgs.shape

3. 数据可视化 

transpose((1, 2, 0))详解:

  • 作用是对NumPy数组进行轴变换,transpose函数的参数是一个元组,定义了新轴的顺序。原始PyTorch张量通常是以(C, H, W)的格式存储的,其中:
    • C是通道数(例如,RGB图像有3个通道)。
    • H是图像的高度。
    • W是图像的宽度。
  • transpose((1, 2, 0))将轴的顺序从(C, H, W)转换为(H, W, C),这使得数据格式更适合可视化和处理。
# Visualize the data
# Specify the figure size (width=20 inches, height=5 inches)
plt.figure(figsize=(20, 5))

# Iterate over the first 20 images
for i, img in enumerate(imgs[:20]):
    # Convert the tensor to a numpy array and remove any singleton dimensions
    npimg = img.numpy().squeeze().transpose((1, 2, 0))  # Ensures the shape is (32, 32, 3)
    
    # Create a subplot grid (2 rows, 10 columns) and plot each image
    plt.subplot(2, 10, i + 1)
    plt.imshow(npimg, cmap=plt.cm.binary) 
    plt.axis('off')  # Turn off the axis

plt.tight_layout()
plt.show()

二、构建简单的CNN网络 

1. torch.nn.Conv2d()详解

函数原型:

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

关键参数说明:

  • in_channels ( int ) – 输入图像中的通道数
  • out_channels ( int ) – 卷积产生的通道数
  • kernel_size ( int or tuple ) – 卷积核的大小
  • stride ( int or tuple , optional ) -- 卷积的步幅。默认值:1
  • padding ( int , tuple或str , optional ) – 添加到输入的所有四个边的填充。默认值:0
  • dilation (int or tuple, optional) - 扩张操作:控制kernel点(卷积核点)的间距,默认值:1。
  • groups(int,可选):将输入通道分组成多个子组,每个子组使用一组卷积核来处理。默认值为 1,表示不进行分组卷积。
  • padding_mode (字符串,可选) – 'zeros', 'reflect', 'replicate'或'circular'. 默认:'zeros'

2. torch.nn.Linear()详解

函数原型:

torch.nn.Linear(in_features, out_features, bias=True, device=None, dtype=None)

关键参数说明:

  • in_features:每个输入样本的大小
  • out_features:每个输出样本的大小

3.  torch.nn.MaxPool2d()详解

函数原型:

torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)

关键参数说明:

  • kernel_size:最大的窗口大小
  • stride:窗口的步幅,默认值为kernel_size
  • padding:填充值,默认为0
  • dilation:控制窗口中元素步幅的参数

 4. 关于卷积层、池化层的计算:

1. 卷积层参数计算

对于一个卷积层,有以下几个重要参数需要确定:

  • 输入尺寸(Height, Width, Depth)
  • 卷积核尺寸(Kernel Size, K \times K
  • 步长(Stride, S
  • 填充(Padding, P

输出特征图的尺寸计算

假设输入特征图尺寸为(H_{in}, W_{in}, C_{in}), 输出特征图的尺寸 (H_{out}, W_{out}, C_{out})的计算公式如下:  

H_{out} = \frac{H_{in} - K + 2P}{S} + 1

W_{out} = \frac{W_{in} - K + 2P}{S} + 1

C_{out} = \text{Number of filters}

参数数量

卷积层的参数数量由以下公式计算:

\text{Parameters} = (K \times K \times D_{in} + 1) \times C_{out}

其中 K \times K \times D_{in}是每个卷积核的参数数量,加上一个偏置项,再乘以卷积核的数量

2. 池化层参数计算

池化层用于减少特征图的尺寸,主要参数包括:

  • 池化核尺寸(K \times K
  • 步长(Stride, S

常见的池化操作包括最大池化(Max Pooling)和平均池化(Average Pooling)。

输出特征图的尺寸计算

H_{out} = \frac{H_{in} - K}{S} + 1

W_{out} = \frac{W_{in} - K}{S} + 1

C_{out} = C_{in}

池化层通常不改变C,只是减小了宽度和高度。

3. 本文模型尺寸详细计算

输入数据

  • 输入尺寸: (3,32,32)
  • 输入深度: 3

经过卷积层 1

  • 卷积核数量: 64
  • 卷积核尺寸: (3,3)
  • 步长: 1
  • 填充: 0

输出尺寸计算:

H_{out} = \frac{32 - 3 + 0}{1} + 1 = 30

W_{out} = \frac{32 - 3 + 0}{1} + 1 = 30

C_{out} = 64

池化层1输出尺寸:

H_{out} = \frac{30 - 2}{2} + 1 = 15

W_{out} = \frac{30 - 2}{2} + 1 = 15

C_{out} = 64

卷积层2输出尺寸:

H_{out} = \frac{15 - 3 + 0}{1} + 1 = 13

W_{out} = \frac{15 - 3 + 0}{1} + 1 = 13

C_{out} = 64

池化层2输出尺寸:

H_{out} = \frac{13 - 2}{2} + 1 = 6

W_{out} = \frac{13 - 2}{2} + 1 = 6

C_{out} = 64

卷积层3输出尺寸:

H_{out} = \frac{6 - 3 + 0}{1} + 1 = 4

W_{out} = \frac{6 - 3 + 0}{1} + 1 = 4

C_{out} = 128

池化层3输出尺寸:

H_{out} = \frac{4 - 2}{2} + 1 = 2

W_{out} = \frac{4 - 2}{2} + 1 = 2

C_{out} = 128

# Define the model
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

加载并打印模型

# Load and print the model
# 将模型转移到GPU中,  此处没有GPU,所以使用CPU
model = Model().to(device)

summary(model)

三、训练模型

1. 设置超参数

# Define the loss function and optimizer
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2. 编写训练函数

# Train the model
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小,一共50000张图片
    num_batches = len(dataloader)   # 批次数目,1563(50000/32)

    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

测试函数和训练函数大致相同,但是由于不进行梯度下降对网络权重进行更新,所以不需要传入优化器

# Test the model
def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小,一共10000张图片
    num_batches = len(dataloader)          # 批次数目,313(10000/32=312.5,向上取整)
    test_loss, test_acc = 0, 0
    
    # 当不进行训练时,停止梯度更新,节省计算内存消耗
    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

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

# Visualize the training and testing accuracy
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()

  • 13
    点赞
  • 14
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值