Python Pytorch 1.5优化器导致.step（）中的就地操作（可能存在错误）

关于。PyTorch提到了这一变化，但我不确定如何应用他们的指导方针，可能只是有一个bug

此代码将显示错误

import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt


# Hyper Parameters
BATCH_SIZE = 64
LR_G = 0.0001
LR_D = 0.0001 
N_IDEAS = 5  
ART_COMPONENTS = 15 
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])


def artist_works():  # painting from the famous artist (real target)
    r = 0.02 * np.random.randn(1, ART_COMPONENTS)
    paintings = np.sin(PAINT_POINTS * np.pi) + r
    paintings = torch.from_numpy(paintings).float()
    return paintings


G = nn.Sequential(  # Generator
    nn.Linear(N_IDEAS, 128),  # random ideas (could from normal distribution)
    nn.ReLU(),
    nn.Linear(128, ART_COMPONENTS),  # making a painting from these random ideas
)

D = nn.Sequential(  # Discriminator
    nn.Linear(ART_COMPONENTS, 128),  # receive art work either from the famous artist or a newbie like G
    nn.ReLU(),
    nn.Linear(128, 1),
    nn.Sigmoid(),  # tell the probability that the art work is made by artist
)

opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)


for step in range(10000):
    artist_paintings = artist_works()  # real painting from artist
    G_ideas = torch.randn(BATCH_SIZE, N_IDEAS)  # random ideas
    G_paintings = G(G_ideas)  # fake painting from G (random ideas)

    prob_artist0 = D(artist_paintings)  # D try to increase this prob
    prob_artist1 = D(G_paintings)  # D try to reduce this prob

    D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
    G_loss = torch.mean(torch.log(1. - prob_artist1))

    opt_D.zero_grad()
    D_loss.backward(retain_graph=True)  # reusing computational graph
    opt_D.step()

    opt_G.zero_grad()
    G_loss.backward()
    opt_G.step()

RuntimeError：梯度计算所需的变量之一已通过就地操作修改：[torch.FloatTensor[128，1]]，它是TBackward的输出0，处于版本4；应改用版本3。

唯一的[128,1]张量参数是

D（）

中的线性层。错误来自

opt_D.step（）

调用中的某个地方，然后在保留的图形上调用

backward（）

传递

发行说明中有以下克隆参数的示例：

def model(input, target, param):
    return (input * param ** 2 - target).norm()

param = torch.randn(2, requires_grad=True)
input = torch.randn(2)
target = torch.randn(2)
sgd = optim.SGD([param], lr=0.001)
loss = model(input, target, param.clone())
loss.backward(retain_graph=True)
sgd.step()
loss.backward()
param.grad

这解决了这里的问题，但不是在初始示例中，因为参数来自鉴别器模型的线性层，所以有点细微差别