1 问题描述

今天在写作DeepLabV3+的代码时，遇到了一个问题，

程序报错：

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [2, 64, 253, 765]], which is output 0 of ReluBackward1, is at version 2; expected version 1 instead.

根据提示信息来说，感觉应该是跟inplace有关的操作出现的问题；

2 解决方案

出现这个问题，我第一时间想到的是就是nn.ReLU()函数出现的问题，因为ReLU()中有一个设置就是是否启用原位操作；

在一般情况下，为了节省内存，都会设置为True；

所以我把所有使用ReLU函数的地方全部排查了一遍，发现问题的原因是使用了两个连续的ReLU(inplace=True)的操作，

触发错误的代码如下：

conv1 = nn.Conv2d(3, 128, kernel_size=1, bias=False)
bn = nn.BatchNorm2d(128)
relu1 = nn.ReLU(inplace = True)
relu2 = nn.ReLU(inplace = True)input = torch.randn(10,3,8,8)
x = conv1(input)
x = bn(x)
x = relu1(x)# the second successive inplace ReLU operation
x = relu2(x)x = x.flatten()
x = torch.sum(x)
x.backward()

已经提交到PyTorch官方的GitHub上：

https://github.com/pytorch/pytorch/issues/34429

3 备忘

3.1 连续使用ReLU(inplace=True)和+=原位操作的bug已经修复

GitHub的上关于“连续使用ReLU(inplace=True)和+=原位操作的bug已经修复”，issue的链接如下：

https://github.com/pytorch/pytorch/issues/5687#issuecomment-412681482

3.2 不能使用原位操作修改叶子节点

PyTorch不允许直接使用原位操作修改叶子节点，如果需要修改，

可以参考下面的链接：https://zhuanlan.zhihu.com/p/38475183

3.3 可以使用Tensor.sum.backward()来辅助定位可能出现错误的代码位置

我们可以使用Tensor.sum.backward()来辅助定位可能出现错误的代码位置；

PyTorch报错“RuntimeError: one of the variables needed for gradient computation has been modified by……”相关推荐

解决一个GAN训练过程中的报错：one of the variables needed for gradient computation has been modified by an inplace
跑一个GAN DEMO , 运行时出错. 出错代码: RuntimeError: one of the variables needed for gradient computation has be ...
【Pytorch】RuntimeError: one of the variables needed for gradient computation has been modified by
0.前言最近在用Pytorch训练网络的时候出现了一个奇怪的错误,找了很久在偶然间试出了解决方法,因此记录一下,以作备忘.但具体原理还不是很清楚,也请各位大佬指教. 1.错误 RuntimeErro ...
Pytorch Bug解决：RuntimeError:one of the variables needed for gradient computation has been modified
Pytorch Bug解决:RuntimeError: one of the variables needed for gradient computation has been modified b ...
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace
报错: RuntimeError: one of the variables needed for gradient computation has been modified by an inpla ...
排坑日记1：RuntimeError: one of the variables needed for gradient computation has been modified
问题描述在使用Pytorch复现DeepFill V1时,报如下错: RuntimeError: one of the variables needed for gradient computati ...
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace o
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace o ...
【完美解决】RuntimeError: one of the variables needed for gradient computation has been modified by an inp
正文在后面,往下拉即可~~~~~~~~~~~~ 欢迎各位深度学习的小伙伴订阅的我的专栏 Pytorch深度学习·理论篇+实战篇(2023版)专栏地址:
one of the variables needed for gradient computation has been modified by an inplace operation
参考:https://www.cnblogs.com/liangzp/p/9207979.html 使用一个pytorch写的模型时,报错:RuntimeError:one of the variab ...
错误处理:one of the variables needed for gradient computation has been modified by inplace operation
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace o ...

PyTorch报错“RuntimeError: one of the variables needed for gradient computation has been modified by……”