版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
使用plt.ion()
实时打印拟合过程:
import numpy as np
import torch
from torch.autograd import Variable
import torch.nn.functional
import matplotlib.pyplot as plt
x=torch.unsqueeze(torch.linspace(-1,1,100),dim=1)
y=x.pow(2)+0.2*torch.rand(x.size())
x,y=Variable(x),Variable(y)
plt.scatter(x.numpy(),y.numpy())
plt.show()
class Net(torch.nn.Module):
def __init__(self,n_feature,n_hidden,n_output):
super(Net,self).__init__()
self.hidden=torch.nn.Linear(n_feature,n_hidden)
self.predict=torch.nn.Linear(n_hidden,n_output)
def forward(self,x):
x=torch.relu(self.hidden(x))
x=self.predict(x)
return x
net=Net(1,10,1)
print(net)
plt.show()
#实时打印
plt.ion()
optimizer=torch.optim.SGD(net.parameters(),lr=0.1)
loss_func=torch.nn.MSELoss()
for t in range(100):
predictioin=net(x)
loss=loss_func(predictioin,y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if t%5==0:
plt.cla()
plt.scatter(x.data.numpy(),y.data.numpy())
plt.plot(x.data.numpy(),predictioin.data.numpy(),'r-',lw=5)
plt.text(0.5,0,'Loss=%.4f' % loss.data.numpy(),fontdict={'size':20,'color':'red'})
plt.pause(0.1)