大佬教程收集整理的这篇文章主要介绍了pytorch线性回归,大佬教程大佬觉得挺不错的,现在分享给大家,也给大家做个参考。
#3.2线性回归从零开始import torchimport numpy as npimport randomnum_inputs = 2num_examples = 1000true_w = [2,-3.4]true_b = 4.2features = torch.randn(num_examples,num_inputs, dtype=torch.float32)labels = true_w[0]*features[:,0]+true_w[1]*features[:,1]labels += torch.tensor(np.random.normal(0,0.01,size=labels.size()),dtype=torch.float32)#labels加上了一点正态分布的随机量print(features[0],labels[0])def data_iter(batch_size,features,labels): #数据读取 num_examples = len(features) inDices = list(range(num_examples)) random.shuffle(inDices)#样本读取是随机的 #打乱顺序编码 for i in range(0,num_examples,batch_sizE): j = torch.LongTensor(inDices[i:min(i+batch_size,num_examples)]) yield features.index_SELEct(0,j),labels.index_SELEct(0,j)batch_size = 10for X,y in data_iter(batch_size,features,labels): print(X,y) break#将权重初始化成均值为0,标准差为0.01的正太随机数,偏差则初始化#为0w = torch.tensor(np.random.normal(0,0.01,(num_inputs,1)),dtype=torch.float32)b = torch.zeros(1,dtype=torch.float32)#对这些参数求梯度来迭代参数值w.requires_grad_(requires_grad=TruE)b.requires_grad_(requires_grad=TruE)#线性回归的矢量计算def linreg(X,w,b): return torch.mm(X,w)+b#定义损失函数def squared_loss(y_hat,y): return (y_hat-y.view(y_hat.size()))**2/2def sgd(params,lr,batch_sizE): for param in params: param.data -= lr*param.grad/batch_size#训练模型lr = 0.03num_epochs = 3net = linregloss = squared_lossfor epoch in range(num_epochs): for X,y in data_iter(batch_size,features,labels): l = loss(net(X,w,b),y).@R_673_8870@ l.BACkWARD() sgd([w,b],lr,batch_sizE) w.grad.data.zero_() b.grad.data.zero_() #梯度的清零 Train_l = loss(net(features,w,b),labels) print('epoch %d,loss %f'%(epoch+1,Train_l.mean().item()))
以上是大佬教程为你收集整理的pytorch线性回归全部内容,希望文章能够帮你解决pytorch线性回归所遇到的程序开发问题。
如果觉得大佬教程网站内容还不错,欢迎将大佬教程推荐给程序员好友。
本图文内容来源于网友网络收集整理提供,作为学习参考使用,版权属于原作者。
如您有任何意见或建议可联系处理。小编QQ:384754419,请注明来意。