任务要求：利用PyTorch框架搭建一个LeNet模型，并针对MNIST数据集进行训练和测试。
数据集：MNIST
导入：
import torchfrom torch import nn, optimfrom torch.autograd import Variablefrom torch.nn import functional as Ffrom torchvision import datasets, transformsfrom torch.utils.data import DataLoaderimport matplotlib.pyplot as plt# %matplotlib inline
use_gpu = True if torch.cuda.is_available() else Falseprint('Use GPU:', use_gpu)
运行结果如下：
Use GPU: True
1. 数据集加载：
利用torchvision的datasets加载MNSIT数据集
transform = pose([transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])batch_size = 64train_dataset = datasets.MNIST(root='./data/', train=True, transform=transform, download=True)print(train_dataset)train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)train_num = len(train_dataset)print('train image num:', train_num)
运行结果如下：
Dataset MNISTNumber of datapoints: 60000Root location: ./data/Split: TrainStandardTransformTransform: Compose(ToTensor()Normalize(mean=[0.5], std=[0.5]))train image num: 60000
test_dataset = datasets.MNIST(root='./data/', train=False, transform=transform, download=True)print(test_dataset)test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=True)test_num = len(test_dataset)print('test image num:', test_num)
运行结果如下：
Dataset MNISTNumber of datapoints: 10000Root location: ./data/Split: TestStandardTransformTransform: Compose(ToTensor()Normalize(mean=[0.5], std=[0.5]))test image num: 10000
2. LeNet模型构建：
利用PyTorch构建LeNet模型类
class LeNet(nn.Module):''' 请在下方编写LeNet模型的代码 '''def __init__(self):super(LeNet,self).__init__()self.conv1 = nn.Conv2d(1, 6, 5, 1,)self.conv2 = nn.Conv2d(6, 16, 5, 1)self.fc1 = nn.Linear(16*4*4, 120)self.fc2 = nn.Linear(120, 84)self.fc3 = nn.Linear(84, 10)def forward(self, x):#x:1*28*28x = F.max_pool2d(self.conv1(x), 2, 2)x = F.max_pool2d(self.conv2(x), 2, 2)x = x.view(-1, 16*4*4)x = self.fc1(x)x = self.fc2(x)x = self.fc3(x)return F.log_softmax(x,dim=1)cnn = LeNet()if use_gpu:cnn = cnn.cuda()print(cnn)
运行结果如下：
LeNet((conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))(conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))(fc1): Linear(in_features=256, out_features=120, bias=True)(fc2): Linear(in_features=120, out_features=84, bias=True)(fc3): Linear(in_features=84, out_features=10, bias=True))
3. 优化器和损失函数：
定义优化器(SGD/Adam)和交叉熵损失函数
# 优化器import torch.optim as optim# ''' 请在下方编写优化器定义代码 '''optimizer = torch.optim.Adam(cnn.parameters(), lr=0.001, betas=(0.9, 0.99))print(optimizer)# output = cnn(data)from torch.nn import functional as F# 损失函数# ''' 请在下方编写损失函数定义代码 '''criterion = nn.CrossEntropyLoss(size_average=False)# loss = F.cross_entropy(output,target) #交叉熵损失函数print(criterion)
运行结果如下：
Adam (Parameter Group 0amsgrad: Falsebetas: (0.9, 0.99)eps: 1e-08lr: 0.001weight_decay: 0)CrossEntropyLoss()
4. 模型训练和测试：
模型训练函数(要求间隔记录输出损失函数及正确率)
# 训练CNN模型def train(epoch):cnn.train()train_loss = 0correct = 0for batch_idx, (data, label) in enumerate(train_loader):''' 请在下方编写计算损失函数、预测正确数、误差反向传播、梯度更新相关代码 '''output = cnn(data)optimizer.zero_grad()loss = criterion(output,label)loss.backward()optimizer.step() #相当于更新权重值pred = output.max(1, keepdim=True)[1] # 找到概率最大的下标correct += pred.eq(label.view_as(pred)).sum().item()# 输出训练阶段loss信息train_loss += loss.item()train_loss_list.append(loss.item())if batch_idx % 200 == 0:print('Train Epoch: {} [{:05d}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(epoch, batch_idx * len(data), train_num,100 * batch_idx * len(data) / train_num, loss.item()))train_loss /= train_numaccuracy = correct / train_numtrain_acc_list.append(accuracy)# 输出训练阶段loss信息print('Train Epoch: {}\tAverage loss: {:.4f}\tAccuracy: {}/{} ({:.2f}%)'.format(epoch, train_loss, correct, train_num, 100.0 * accuracy))
模型测试函数(要求间隔记录输出损失函数及正确率)
# 测试CNN模型def test():cnn.eval()test_loss = 0correct = 0for data, label in test_loader:if use_gpu: # 使用GPUdata, label = Variable(data).cuda(), Variable(label).cuda()''' 请在下方编写计算损失函数、预测正确数相关代码 '''output = cnn(data)loss = criterion(output, label) # 将一批的损失相加pred = output.max(1, keepdim=True)[1] # 找到概率最大的下标correct += pred.eq(label.view_as(pred)).sum().item()test_loss += loss.item()test_loss_list.append(loss.item())test_loss /= test_numaccuracy = correct / test_numtest_acc_list.append(accuracy)# 输出测试阶段loss信息print('Test Epoch: {}\tAverage loss: {:.4f}\tAccuracy: {}/{} ({:.2f}%)\n'.format(epoch, test_loss, correct, test_num, 100.0 * accuracy))
train_loss_list = []test_loss_list = []train_acc_list = []test_acc_list = []epoch_num = 10for epoch in range(1, epoch_num+1):# 每轮训练完测试train(epoch)test()
5. 损失函数和正确率曲线：
训练损失函数图 & 测试损失函数图 & 训练/测试正确率图
plt.figure(figsize=(12,6))plt.plot(train_loss_list)plt.title('train loss', fontsize=18)plt.xticks(fontsize=14)plt.yticks(fontsize=14)plt.grid()plt.show()plt.figure(figsize=(12,6))plt.plot(test_loss_list)plt.title('test loss', fontsize=18)plt.xticks(fontsize=14)plt.yticks(fontsize=14)plt.grid()plt.show()plt.figure(figsize=(12,8))plt.plot(train_acc_list, 'o-')plt.plot(test_acc_list, 'o-')plt.title('Accuracy', fontsize=18)plt.xlabel('Epoch', fontsize=16)plt.ylabel('Accuracy', fontsize=16)plt.xticks(fontsize=14)plt.yticks(fontsize=14)plt.legend(['Train', 'Test'], fontsize=16)plt.grid()plt.show()
运行结果如下：
