CNN简单实战：pytorch搭建CNN对猫狗图片进行分类

全栈程序员-站长 • 2022年6月12日下午9:16 • 未分类 • 阅读 24

大家好，又见面了，我是你们的朋友全栈君。

在上一篇文章：CNN训练前的准备：pytorch处理自己的图像数据（Dataset和Dataloader），大致介绍了怎么利用pytorch把猫狗图片处理成CNN需要的数据，今天就用该数据对自己定义的CNN模型进行训练及测试。

首先导入需要的包：

import torch
from torch import optim
import torch.nn as nn
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image

定义自己的CNN网络

class cnn(nn.Module):
    def __init__(self):
        super(cnn, self).__init__()
        self.relu = nn.ReLU()
        self.sigmoid = nn.Sigmoid()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=3,
                out_channels=16,
                kernel_size=3,
                stride=2,
            ),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        #
        self.conv2 = nn.Sequential(
            nn.Conv2d(
                in_channels=16,
                out_channels=32,
                kernel_size=3,
                stride=2,
            ),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        #
        self.conv3 = nn.Sequential(
            nn.Conv2d(
                in_channels=32,
                out_channels=64,
                kernel_size=3,
                stride=2,
            ),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        self.fc1 = nn.Linear(3 * 3 * 64, 64)
        self.fc2 = nn.Linear(64, 10)
        self.out = nn.Linear(10, 2)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        # print(x.size())
        x = x.view(x.shape[0], -1)
        x = self.relu(self.fc1(x))
        x = self.relu(self.fc2(x))
        x = self.out(x)
        return x

训练（GPU）

def train():
    train_loader, test_loader = load_data()
    print('train...')
    epoch_num = 15
    # GPU
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model = cnn().to(device)
    optimizer = optim.Adam(model.parameters(), lr=0.0008)
    criterion = nn.CrossEntropyLoss().to(device)
    for epoch in range(epoch_num):
        for batch_idx, (data, target) in enumerate(train_loader, 0):
            data, target = Variable(data).to(device), Variable(target.long()).to(device)
            optimizer.zero_grad()
            output = model(data)
            loss = criterion(output, target)
            loss.backward()
            optimizer.step()
            if batch_idx % 10 == 0:
                print('Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                    epoch, batch_idx * len(data), len(train_loader.dataset),
                           100. * batch_idx / len(train_loader), loss.item()))

    torch.save(model.state_dict(), "model/cnn.pkl")

一共训练三轮，训练的步骤如下：

初始化模型：

model = cnn().to(device)

选择优化器以及优化算法，这里选择了Adam：

optimizer = optim.Adam(model.parameters(), lr=0.00005)

选择损失函数，这里选择了交叉熵：

criterion = nn.CrossEntropyLoss().to(device)

对每一个batch里的数据，先将它们转成能被GPU计算的类型：

 data, target = Variable(data).to(device), Variable(target.long()).to(device)

梯度清零、前向传播、计算误差、反向传播、更新参数：

optimizer.zero_grad()  # 梯度清0
output = model(data)[0]  # 前向传播
loss = criterion(output, target)  # 计算误差
loss.backward()  # 反向传播
optimizer.step()  # 更新参数

测试（GPU）

def test():
    train_loader, test_loader = load_data()
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model = torch.load('cnn.pkl')  # load model
    total = 0
    current = 0
    for data in test_loader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)[0]

        predicted = torch.max(outputs.data, 1)[1].data
        total += labels.size(0)
        current += (predicted == labels).sum()

    print('Accuracy: %d %%' % (100 * current / total))