pytorch实现个人手写数字识别_pytorch 测试自己的数字

网上的大多数例子都是基于Mnist数据集进行测试的，今天实现一个自己手写数字的识别。

 

首先训练模型，使用Mnist数据集，网络的backbone采用LeNet。

1. 导入需要的模块并添加GPU设备

import torch
import torchvision as tv
import torchvision.transforms as transforms
import torch.nn as nn
import torch.optim as optim
import cv2
 
# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

2. 定义网络结构

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Sequential(  # input_size=(1*28*28)
            nn.Conv2d(1, 6, 5, 1, 2),  # padding=2保证输入输出尺寸相同
            nn.ReLU(),  # input_size=(6*28*28)
            nn.MaxPool2d(kernel_size=2, stride=2),  # output_size=(6*14*14)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(6, 16, 5),
            nn.ReLU(),  # input_size=(16*10*10)
            nn.MaxPool2d(2, 2)  # output_size=(16*5*5)
        )
        self.fc1 = nn.Sequential(
            nn.Linear(16 * 5 * 5, 120),
            nn.ReLU()
        )
        self.fc2 = nn.Sequential(
            nn.Linear(120, 84),
            nn.ReLU()
        )
        self.fc3 = nn.Linear(84, 10)
 
    # 定义前向传播过程，输入为x
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        # nn.Linear()的输入输出都是维度为一的值，所以要把多维度的tensor展平成一维（一行）
        x = x.view(x.size()[0], -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x

3. 设置超参数和定义训练和测试数据提取器

# 超参数设置
EPOCH = 10 # 遍历数据集次数
BATCH_SIZE = 256  # 批处理尺寸(batch_size)
LR = 0.001  # 学习率
 
# 定义数据预处理方式
transform = transforms.ToTensor()
 
# 定义训练数据集
trainset = tv.datasets.MNIST(
    root='./data/',
    train=True,
    download=False,
    transform=transform)
 
# 定义训练批处理数据
trainloader = torch.utils.data.DataLoader(
    trainset,
    batch_size=BATCH_SIZE,
    shuffle=True,
)
 
# 定义测试数据集
testset = tv.datasets.MNIST(
    root='./data/',
    train=False,
    download=False,
    transform=transform)

4. 定义训练函数

def train():
    # 定义损失函数loss function 和优化方式（采用SGD）
    net = LeNet().to(device)
    criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数，通常用于多分类问题上
    optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)
    for epoch in range(EPOCH):
        sum_loss = 0.0
        # 数据读取
        for i, data in enumerate(trainloader):
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)
 
            # 梯度清零
            optimizer.zero_grad()
 
            # forward + backward
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
 
            # 每训练100个batch打印一次平均loss
            sum_loss += loss.item()
            if i % 100 == 99:
                print('[%d, %d] loss: %.03f'
                      % (epoch + 1, i + 1, sum_loss / 100))
                sum_loss = 0.0
        # 每跑完一次epoch测试一下准确率
        with torch.no_grad():
            correct = 0
            total = 0
            for data in testloader:
                images, labels = data
                images, labels = images.to(device), labels.to(device)
                outputs = net(images)
                # 取得分最高的那个类
                _, predicted = torch.max(outputs.data, 1)
                total += labels.size(0)
                correct += (predicted == labels).sum()
            print('第%d个epoch的识别准确率为：%d%%' % (epoch + 1, (100 * correct / total)))
        # 保存模型参数
        torch.save(net.state_dict(), './params.pth')

5. 先进行训练，训练结果会保存在params.pth中。

if __name__ == "__main__":
    train()

6. 训练完成后注释掉训练函数，读取训练好的模型参数并进行测试。

# 读取训练好的网络参数
net = LeNet().to(device)
a = torch.load('./params.pth')
net.load_state_dict(torch.load('./params.pth'))
 
 
if __name__ == "__main__":
    # train()
    img = cv2.imread('./2.png', cv2.IMREAD_GRAYSCALE) #读取图片
    img = cv2.resize(img,(28, 28))  # 调整图片为28*28
    img = torch.from_numpy(img).float()
    img = img.view(1, 1, 28, 28)
    img = img.to(device)
    outputs = net(img)
    _, predicted = torch.max(outputs.data, 1)
    print(predicted.to('cpu').numpy().squeeze())

测试图片使用windows软件画图绘制，如下：

输出结果如下：

完整代码如下：

import torch
import torchvision as tv
import torchvision.transforms as transforms
import torch.nn as nn
import torch.optim as optim
import cv2
 
# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 
# 定义网络结构
class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Sequential(  # input_size=(1*28*28)
            nn.Conv2d(1, 6, 5, 1, 2),  # padding=2保证输入输出尺寸相同
            nn.ReLU(),  # input_size=(6*28*28)
            nn.MaxPool2d(kernel_size=2, stride=2),  # output_size=(6*14*14)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(6, 16, 5),
            nn.ReLU(),  # input_size=(16*10*10)
            nn.MaxPool2d(2, 2)  # output_size=(16*5*5)
        )
        self.fc1 = nn.Sequential(
            nn.Linear(16 * 5 * 5, 120),
            nn.ReLU()
        )
        self.fc2 = nn.Sequential(
            nn.Linear(120, 84),
            nn.ReLU()
        )
        self.fc3 = nn.Linear(84, 10)
 
    # 定义前向传播过程，输入为x
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        # nn.Linear()的输入输出都是维度为一的值，所以要把多维度的tensor展平成一维（一行）
        x = x.view(x.size()[0], -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x
 
 
 
 
# 使得我们能够手动输入命令行参数，就是让风格变得和Linux命令行差不多
# parser = argparse.ArgumentParser()
# parser.add_argument('--outf', default='./model/', help='folder to output images and model checkpoints')  # 模型保存路径
# parser.add_argument('--net', default='./model/net.pth', help="path to netG (to continue training)")  # 模型加载路径
# opt = parser.parse_args()
 
# 超参数设置
EPOCH = 10 # 遍历数据集次数
BATCH_SIZE = 256  # 批处理尺寸(batch_size)
LR = 0.001  # 学习率
 
# 定义数据预处理方式
transform = transforms.ToTensor()
 
# 定义训练数据集
trainset = tv.datasets.MNIST(
    root='./data/',
    train=True,
    download=False,
    transform=transform)
 
# 定义训练批处理数据
trainloader = torch.utils.data.DataLoader(
    trainset,
    batch_size=BATCH_SIZE,
    shuffle=True,
)
 
# 定义测试数据集
testset = tv.datasets.MNIST(
    root='./data/',
    train=False,
    download=False,
    transform=transform)
 
# 定义测试批处理数据
testloader = torch.utils.data.DataLoader(
    testset,
    batch_size=BATCH_SIZE,
    shuffle=False,
)
 
# 定义损失函数loss function 和优化方式（采用SGD）
net = LeNet().to(device)
a = torch.load('./params.pth')
net.load_state_dict(torch.load('./params.pth'))
criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数，通常用于多分类问题上
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)
 
# 训练并保存模型参数
def train():
 
    for epoch in range(EPOCH):
        sum_loss = 0.0
        # 数据读取
        for i, data in enumerate(trainloader):
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)
 
            # 梯度清零
            optimizer.zero_grad()
 
            # forward + backward
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
 
            # 每训练100个batch打印一次平均loss
            sum_loss += loss.item()
            if i % 100 == 99:
                print('[%d, %d] loss: %.03f'
                      % (epoch + 1, i + 1, sum_loss / 100))
                sum_loss = 0.0
        # 每跑完一次epoch测试一下准确率
        with torch.no_grad():
            correct = 0
            total = 0
            for data in testloader:
                images, labels = data
                images, labels = images.to(device), labels.to(device)
                outputs = net(images)
                # 取得分最高的那个类
                _, predicted = torch.max(outputs.data, 1)
                total += labels.size(0)
                correct += (predicted == labels).sum()
            print('第%d个epoch的识别准确率为：%d%%' % (epoch + 1, (100 * correct / total)))
        # 保存模型参数
        torch.save(net.state_dict(), './params.pth')
 
if __name__ == "__main__":
    # train()
    img = cv2.imread('./2.png', cv2.IMREAD_GRAYSCALE)
    img = cv2.resize(img,(28, 28))
    img = torch.from_numpy(img).float()
    img = img.view(1, 1, 28, 28)
    img = img.to(device)
    outputs = net(img)
    _, predicted = torch.max(outputs.data, 1)
    print(predicted.to('cpu').numpy().squeeze())