import torch as t
from torch.autograd import Variable as V
from matplotlib import pyplot as plt
#随机数种子
t.manual_seed(1000)
def get_fake_data(batch_size=8):
'''产生随即数据y=2x+3,并添加噪声'''
x=t.rand(batch_size,1)*20
y=2*x+(1+t.randn(batch_size,1))*3
return x,y
x,y=get_fake_data()
#plt.scatter(x.squeeze().numpy(),y.squeeze().numpy())
#初始化w,b
w=V(t.rand(1,1),requires_grad=True)
b=V(t.zeros(1,1),requires_grad=True)
#学习率
lr=0.001
for i in range(8000):
x,y=get_fake_data()
x,y=V(x),V(y)
#前向传播,mm为矩阵乘法
y_pred=x.mm(w)+b.expand_as(y)
loss=0.5*(y_pred-y)**2
loss=loss.sum()
#反向传播
loss.backward()
#梯度下降法更新参数
w.data.sub_(lr*w.grad.data)
b.data.sub_(lr*b.grad.data)
#梯度清零
w.grad.data.zero_()
b.grad.data.zero_()
#绘图
xx=t.range(0,20).view(-1,1)
yy=xx.mm(w.data)+b.data.expand_as(xx)
plt.plot(xx.numpy(),yy.numpy())
x2,y2=get_fake_data(batch_size=20)
plt.scatter(x2.numpy(),y2.numpy())
plt.xlim(0,20)
plt.ylim(0,41)
plt.show()
截图如下: