使用Pytorch训练two-head网络的操作

f_out_y0, _ = net(x0)
_, f_out_y1 = net(x1)
#实例化损失函数
criterion0 = Loss()
criterion1 = Loss()
loss0 = criterion0(f_y0, f_out_y0, w0)
loss1 = criterion1(f_y1, f_out_y1, w1)
print(loss0.item(), loss1.item())
#对网络参数进行初始化
optimizer.zero_grad()
loss0.backward()
loss1.backward()
#对网络的参数进行更新
optimizer.step()

f_out_y0, cf_out_y0 = net(x0)
cf_out_y1, f_out_y1 = net(x1)
#按照t=0和t=1的索引拼接向量
y_pred = torch.zeros([len(x), 1])
y_pred[index0] = f_out_y0
y_pred[index1] = f_out_y1

criterion = Loss()
loss = criterion(f_y, y_pred, w) + 0.01 * (l2_regularization0 + l2_regularization1)
#print(loss.item())
viz.line([float(loss)], [epoch], win='train_loss', update='append')
optimizer.zero_grad()
loss.backward()
#对网络的参数进行更新
optimizer.step()

import torch 
print(torch.tensor([1,2,3],dtype=torch.float))#将一个列表强制转换为torch.Tensor类型
print(torch.randn(5,3))#生成torch.Tensor类型的5X3的随机数

import torch
from torch.autograd import Variable
 
#初步认识构建Tensor数据
def one():
 print(torch.tensor([1,2,3],dtype=torch.float))#将一个列表强制转换为torch.Tensor类型
 print(torch.randn(5,3))#生成torch.Tensor类型的5X3的随机数
 print(torch.zeros((2,3)))#生成一个2X3的全零矩阵
 print(torch.ones((2,3)))#生成一个2X3的全一矩阵
 a = torch.randn((2,3))
 b = a.numpy()#将一个torch.Tensor转换为numpy
 c = torch.from_numpy(b)#将numpy转换为Tensor
 print(a)
 print(b)
 print(c)
 
#使用Variable自动求导
def two():
 # 构建Variable
 x = Variable(torch.Tensor([1, 2, 3]), requires_grad=True)
 w = Variable(torch.Tensor([4, 5, 6]), requires_grad=True)
 b = Variable(torch.Tensor([7, 8, 9]), requires_grad=True)
 # 函数等式
 y = w * x ** 2 + b
 # 使用梯度下降计算各变量的偏导数
 y.backward(torch.Tensor([1, 1, 1]))
 print(x.grad)
 print(w.grad)
 print(b.grad)

import torch
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
from torch import nn
 
x = torch.unsqueeze(torch.linspace(-1,1,100),dim=1)
y = 3*x+10+torch.rand(x.size())
class LinearRegression(nn.Module):
 def __init__(self):
  super(LinearRegression,self).__init__()
  self.Linear = nn.Linear(1,1)
 def forward(self,x):
  return self.Linear(x)
model = LinearRegression()
Loss = nn.MSELoss()
Opt = torch.optim.SGD(model.parameters(),lr=0.01)
for i in range(1000):
 inputs = Variable(x)
 targets = Variable(y)
 outputs = model(inputs)
 loss = Loss(outputs,targets)
 Opt.zero_grad()
 loss.backward()
 Opt.step()
model.eval()
predict = model(Variable(x))
plt.plot(x.numpy(),y.numpy(),'ro')
plt.plot(x.numpy(),predict.data.numpy())
plt.show()