RuntimeError：梯度计算所需的变量之一已被就地操作修改？

Question

我正在使用pytorch-1.5 做一些gan 测试。我的代码是非常简单的 gan 代码，正好适合 sin(x) 函数：

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()

但是当我运行它时出现了这个错误：

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [128, 1]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

我的代码有问题吗？

Answer 1

它在 1.4 上工作但在 1.5 中出错的一般原因是因为“在 1.5 之前，这些测试对于优化器来说不能正常工作。这就是为什么你没有看到任何错误。但计算出的梯度不正确。'

更多关于版本影响的讨论可以查看这个链接：https://discuss.pytorch.org/t/solved-pytorch1-5-runtimeerror-one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation/90256/4

Answer 2

发生这种情况是因为 opt_D.step() 就地修改了鉴别器的参数。但是这些参数是计算生成器的梯度所必需的。您可以通过将代码更改为：

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_artist1 = D(G_paintings)  # G tries to fool D

    G_loss = torch.mean(torch.log(1. - prob_artist1))
    opt_G.zero_grad()
    G_loss.backward()
    opt_G.step()

    prob_artist0 = D(artist_paintings)  # D try to increase this prob
    # detach here to make sure we don't backprop in G that was already changed.
    prob_artist1 = D(G_paintings.detach())  # D try to reduce this prob

    D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
    opt_D.zero_grad()
    D_loss.backward(retain_graph=True)  # reusing computational graph
    opt_D.step()

你可以在这里https://github.com/pytorch/pytorch/issues/39141找到更多关于这个问题的信息