MNIST手写数字识别代码详细备注版【零基础入门使用】

详细讲解视频可看B站up：唐国梁Tommy的视频轻松学 PyTorch 手写字体识别 MNIST
这是我目前为止看到的讲解最详细的视频，解答了我很疑惑。

😁
下面放了两个版本的代码，第一个是上面up主讲解的代码，下面的那个是pytorch官方给出的mnist代码。

官方代码链接：github

一、详细备注版

#来自b站up唐国梁Tommy

# 1 加载必要的库
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import cv2
import numpy as np

# 2 定义超参数
BATCH_SIZE = 64 # 每批处理的数据
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 使用GPU或者CPU训练
EPOCHS = 10 #训练数据集的轮次
# 3 构建pipeline，对图像进行处理
pipeline = transforms.Compose([
    transforms.ToTensor(), # 将图片转换成tensor
    transforms.Normalize((0.1307,),(0.3081)) # 降低模型的复杂度
])

# 4 下载，加载数据
train_set = datasets.MNIST("data",train=True,download=True,transform=pipeline)

test_set = datasets.MNIST("data",train=False,download=True,transform=pipeline)

# 加载数据
train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True)

test_loader = DataLoader(test_set, batch_size=BATCH_SIZE, shuffle=True)

# 显示MNIST中的图片
# with open("./data/MNIST/raw/train-images-idx3-ubyte","rb") as f:
# #     file = f.read()
# #
# # image1 = [int(str(item).encode('ascii'),10) for item in file[16 : 16+784]]
# # print(image1)
# #
# # image1_np = np.array(image1, dtype=np.uint8).reshape(28, 28, 1)
# # print(image1_np.shape)
# #
# # cv2.imwrite("digit.jpg", image1_np)

# 5 构建网络模型
class Netmodel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 10, 5) # 1: 灰度图片的通道，10：输出通道，5：kernel卷积核大小
        self.conv2 = nn.Conv2d(10, 20, 3) # 10:输入通道，20：输出通道，3：kernel
        self.fc1 = nn.Linear(20*10*10, 500) #20*10*10：输入通道，500：输出通道
        self.fc2 = nn.Linear(500, 10) # 500：输入通道，10：输出通道

    def forward(self,x):
        input_size = x.size(0) # batch_size
        x = self.conv1(x) # 输入：batch*1*28，输出：batch*10*24*24 (28-5+1=24) 卷积 *** 作
        x = F.relu(x) # 保持shape不变，输出：batch*10*24*24
        x = F.max_pool2d(x, 2, 2) # 输入：batch*10*24*24 输出：batch*10*12*12

        x = self.conv2(x) # 输入：batch*10*12*12 输出：batch*20*10*10
        x =  F.relu(x)

        x = x.view(input_size,-1) # Flatten的作用 -1，自动计算维度， 20*10*10 = 2000

        x = self.fc1(x) # 输入：batch*2000 输出：batch*500
        x = F.relu(x) # 保持shape不变

        x = self.fc2(x) # 输入：batch*500 输出：batch*10

        output = F.log_softmax(x, dim=1) # 计算分类后，每个数字的概率值

        return output


# 6 定义优化器
model = Netmodel().to(DEVICE)
optimizer = optim.Adam(model.parameters())

# 7 定义训练方法
def train_model(model, device, train_loader, optimizer, epoch):
    # 模型训练
    model.train()
    for batch_index, (data, target) in enumerate(train_loader):
        # 部署到DEVICE上去
        data, target = data.to(device), target.to(device)
        # 梯度初始化为0
        optimizer.zero_grad()
        # 训练后的结果
        output = model(data)
        # 计算损失
        loss = F.cross_entropy(output, target)
        # 反向传播
        loss.backward()
        # 参数优化
        optimizer.step()
        if batch_index % 3000 == 0:
            print("Train Epoch : {}\t Loss : {:.6f}".format(epoch, loss.item()))

# 8 定义测试方法
def test_model(model, device, test_loader):
    # 模型验证
    model.eval()
    # 正确率
    correct = 0.0
    # 测试损失
    test_loss= 0.0
    with torch.no_grad(): # 不会计算梯度，也不会进行反向传播
        for data, target in test_loader:
            # 部署到device
            data, target = data.to(device), target.to(device)
            # 测试数据
            output = model(data)
            # 计算测试损失
            test_loss += F.cross_entropy(output, target).item()
            # 找到概率值最大的下标
            pred = output.max(1, keepdim=True)[1] # 值，索引
            # pred = torch.max(output, dim=1)
            # pred = output.argmax(dim=1)
            # 累计正确的值
            correct += pred.eq(target.view_as(pred)).sum().item()
        test_loss /= len(test_loader.dataset)
        print("Test —— Average loss : {:.4f}, Accuracy : {:.3f}\n".format(
            test_loss, 100.0 * correct / len(test_loader.dataset)
        ))

# 9 调用方法
for epoch in range(1,EPOCHS +1):
    train_model(model, DEVICE, train_loader, optimizer, epoch)
    test_model(model, DEVICE,test_loader)

二、pytorch官方mnist示例

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
            if args.dry_run:
                break


def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.4f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=14, metavar='N',
                        help='number of epochs to train (default: 14)')
    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
                        help='learning rate (default: 1.0)')
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--dry-run', action='store_true', default=False,
                        help='quickly check a single pass')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--save-model', action='store_true', default=False,
                        help='For Saving the current Model')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    train_kwargs = {'batch_size': args.batch_size}
    test_kwargs = {'batch_size': args.test_batch_size}
    if use_cuda:
        cuda_kwargs = {'num_workers': 1,
                       'pin_memory': True,
                       'shuffle': True}
        train_kwargs.update(cuda_kwargs)
        test_kwargs.update(cuda_kwargs)

    transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
        ])
    dataset1 = datasets.MNIST('data', train=True, download=True,
                       transform=transform)
    dataset2 = datasets.MNIST('data', train=False,
                       transform=transform)
    train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs)
    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)

    model = Net().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)
        scheduler.step()

    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")


if __name__ == '__main__':
    main()