损失函数在pytorch中没有requires_grad=True

Question

您好，我有以下代码（我的代码的简化版本，但能够重现错误）：

import numpy as np
from numpy import linalg as LA
import torch
import torch.optim as optim 
import torch.nn as nn

def func(x,pars):
    a = pars[0]
    b = pars[1]
    c = pars[2]
    d = pars[3]

    x = x.int()

    H = torch.tensor([[a,b,1],[2,3,c],[4,d,7]])

    eigenvalues, eigenvectors = np.linalg.eigh(H)

    trans_freq = eigenvalues[x]

    return torch.tensor(trans_freq)

x_index = torch.tensor([1,2])
y_vals = torch.tensor([0.5,12])

params = torch.tensor([1.,2.,3.,4.])
params.requires_grad=True
opt = optim.SGD([params], lr=100)

mse_loss = nn.MSELoss()

for i in range(10):
  opt.zero_grad()
  loss = mse_loss(func(x_index,params),y_vals)
  print(x_index.requires_grad)
  print(params.requires_grad)
  print(y_vals.requires_grad)
  print(loss.requires_grad)
  loss.backward()
  opt.step() 
  print(loss)

输出为：

False
True
False
False

并且我收到此错误：

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

，来自此行：

loss.backward()

。事实上，损失没有

requires_grad=True

但为什么会这样（在 for 循环中手动设置它也不起作用）。我应该怎么办？谢谢！

Answer 1

您需要在

loss.requires_grad = True

 之前添加一行 

loss.backward()

for i in range(10):
  opt.zero_grad()
  loss = mse_loss(func(x_index,params),y_vals)
  print(x_index.requires_grad)
  print(params.requires_grad)
  print(y_vals.requires_grad)
  print(loss.requires_grad)

  loss.requires_grad = True     # Here you need to add this line
  loss.backward()
  opt.step() 
  print(loss)