1 导入实验所需要的包
import torch import torch.nn as nn import numpy as np import torchvision import torchvision.transforms as transforms import matplotlib.pyplot as plt
2 下载MNIST数据集和读取数据
#下载MNIST手写数字数据集 mnist_train = torchvision.datasets.MNIST(root='../Datasets/MNIST', train=True,download=True, transform=transforms.ToTensor()) mnist_test = torchvision.datasets.MNIST(root='../Datasets/MNIST', train=False, download=True, transform=transforms.ToTensor()) #读取数据 batch_size = 32 train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True,num_workers=0) test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False,num_workers=0)
3 定义模型参数
#训练次数和学习率 num_epochs ,lr = 50, 0.01
4 定义模型
class LinearNet(nn.Module): def __init__(self,num_inputs, num_outputs, num_hiddens): super(LinearNet,self).__init__() self.linear1 = nn.Linear(num_inputs,num_hiddens) self.relu = nn.ReLU() self.linear2 = nn.Linear(num_hiddens,num_outputs) def forward(self,x): x = self.linear1(x) x = self.relu(x) x = self.linear2(x) y = self.relu(x) return y
5 定义训练函数
def train(net,train_iter,test_iter,loss,num_epochs,batch_size,params=None,lr=None,optimizer=None): train_ls, test_ls = [], [] for epoch in range(num_epochs): ls, count = 0, 0 for X,y in train_iter: X = X.reshape(-1,num_inputs) l=loss(net(X),y) optimizer.zero_grad() l.backward() optimizer.step() ls += l.item() count += y.shape[0] train_ls.append(ls) ls, count = 0, 0 for X,y in test_iter: X = X.reshape(-1,num_inputs) l=loss(net(X),y) ls += l.item() count += y.shape[0] test_ls.append(ls) if(epoch+1)%5==0: print('epoch: %d, train loss: %f, test loss: %f'%(epoch+1,train_ls[-1],test_ls[-1])) return train_ls,test_ls
6 模型训练
different_hiddens = [100,200,300,400,500,600,700] #定义输入层神经元个数和输出层神经元个数 num_inputs, num_outputs = 784, 10 #定义损失函数 loss = nn.CrossEntropyLoss() Train_loss, Test_loss = [], [] for cur_hiddens in different_hiddens: net = LinearNet(num_inputs, num_outputs, cur_hiddens) optimizer = torch.optim.SGD(net.parameters(),lr = 0.001) for param in net.parameters(): nn.init.normal_(param,mean=0, std= 0.01) train_ls, test_ls = train(net,train_iter,test_iter,loss,num_epochs,batch_size,net.parameters,lr,optimizer) Train_loss.append(train_ls) Test_loss.append(test_ls)
7 绘制不同隐藏单元损失图
x = np.linspace(0,len(train_ls),len(train_ls)) plt.figure(figsize=(10,8)) for i in range(0,len(different_hiddens)): plt.plot(x,Train_loss[i],label= f'Neuronss:{different_hiddens[i]}',linewidth=1.5) plt.xlabel('epoch') plt.ylabel('loss') plt.legend() plt.title('Train loss vs different hiddens') plt.show()