赞
踩
- # 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
- # 2 定义超参数hyperparameter
- BATCH_SIZE = 64 # 每批处理的数据
- DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 是否用GPU还是CPU训练
- EPOCHS = 30 # 训练数据集的轮次数
- # 3 构建pipeline,对图像做处理transforms
- pipeline = transforms.Compose([
- transforms.ToTensor(), # 将图片转换成tensor
- transforms.Normalize((0.1307,), (0.3081,)) # 正则化(均值,标准差)-->当模型过拟合overfitting时可以降低模型复杂度
- ])
- # 4 下载、加载数据集
- from torch.utils.data import DataLoader
-
- # 下载数据集
- train_set = datasets.MNIST("dataset", train=True, download=True, transform=pipeline)
-
- test_set = datasets.MNIST("dataset", train=True, download=True, transform=pipeline)
-
- # 加载数据集
- train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True)
-
- test_loader = DataLoader(test_set, batch_size=BATCH_SIZE, shuffle=True)
- # 5 构建网络模型
- class Digit(nn.Module):
- def __init__(self):
- super().__init__()
- self.conv1 = nn.Conv2d(1, 10, 5) #第一个卷积层(1:输入的灰度图的通道,10:输出通道,5:卷积层Kernel)
- self.conv2 = nn.Conv2d(10, 20, 3) #第二个卷积层(10:输入通道,20:输出通道,3:卷积层Kernel)
- self.fc1 = nn.Linear(20*10*10, 500) #第一个全连接层(20*10*10:输入通道,500:输出通道)
- self.fc2 = nn.Linear(500, 10) #第二个全连接层(500:输入通道,10:输出通道【0~9】)
-
- def forward(self, x):
- input_size = x.size(0) # batch_size
- x = self.conv1(x) # 输入:batch*1*28*28,输出:batch*10*24*24 (28-5+1=24)
- x = F.relu(x) #激活函数,保持shape不变,输出:batch*10*24*24
- x = F.max_pool2d(x, 2, 2) #池化层 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 (12-3+1=10)
- x = F.relu(x) #
-
- x = x.view(input_size, -1) # 拉平, -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) # 激活, 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0~9的概率
-
- return output
- # 6 定义优化器
- model = Digit().to(DEVICE)
-
- optimizer = optim.Adam(model.parameters())
- # 7 定义训练函数
- def train_model(model, device, train_loader, optimizer, epoch):
- # 模型训练
- model.train()
- for batch_index, (img, target) in enumerate(train_loader):
- # 将数据部署到DEVICE上去
- img, target = img.to(device), target.to(device)
- # 梯度初始化为0
- optimizer.zero_grad()
- # 训练后的结果
- output = model(img)
- # 计算loss
- loss = F.cross_entropy(output, target) #cross_entropy适合多分类问题,将计算结果与真实值对比
- # 反向传播
- loss.backward()
- # 参数优化
- optimizer.step() # 用step方法更新参数
- # 每隔3000张图片打印一次loss
- 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()
- # 初始化正确率
- correct = 0.0
- # 初始化测试loss
- test_loss = 0.0
- with torch.no_grad(): # 测试时不会计算梯度,也不会进行反向传播
- for img, target in test_loader:
- # 部署到DEVICE上
- img, target = img.to(device), target.to(device)
- # 测试数据
- output = model(img)
- # 计算测试损失
- test_loss += F.cross_entropy(output, target).item()
- # 找到概率最大下标
- pred = output.max(1, keepdim=True)[1] #值,索引
- # pred = output.argmax(dim=1)
- # pred = torch.max(output, 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 * correct / len(test_loader.dataset)))
- # 9 调用方法7、8
- for epoch in range(1, EPOCHS + 1):
- train_model(model, DEVICE, train_loader, optimizer, epoch)
- test_model(model, DEVICE, test_loader)
运行后即可打印出训练信息
具体搭建视频可参考03-2 轻松学 PyTorch 手写字体识别 MNIST ( 实战 - 上 )_哔哩哔哩_bilibilihttps://www.bilibili.com/video/BV1WT4y177SA
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。