RuntimeError: one of the variables needed for gradient computation has been modified by an inplace o

最新推荐文章于 2025-05-21 11:59:08 发布

原创最新推荐文章于 2025-05-21 11:59:08 发布 · 714 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python

深度学习同时被 2 个专栏收录

38 篇文章

订阅专栏

Pytorch

14 篇文章

订阅专栏

在运行PyTorch模型时遇到一个错误：`RuntimeError: oneofthevariablesneededforgradientcomputationhasbeenmodifiedbyaninplaceoperation`。原因是对softmax输出进行了就地修改。为解决此问题，需要在修改softmax输出之前先将其detach()，以防止影响梯度计算。修复方法是将涉及softmax的部分改为：`lu_similarity=lu_similarity.detach()`，然后执行`semantic_p=torch.softmax(lu_similarity,dim=1)`。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

问题

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 2]], which is output 0 of SoftmaxBackward, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

由于我对softmax输出的值就行了修改，出现如上报错

filter_value = float(0)
# 把大于top-k的值置于0，留下小的
indices_to_remove = semantic_p[j] > torch.topk(semantic_p[j], 1, largest=False)[0][..., -1, None
semantic_p[j][indices_to_remove] = filter_value
lu_s_similarity[j][indices_to_remove] = filter_value
s_pse_data2.append(lu_s_similarity[j])
pselabel2.append(semantic_p[j])

解决办法

对需要softmax的值就行如下操作，再进行softmax

lu_similarity = lu_similarity.detach()
semantic_p = torch.softmax(lu_similarity, dim=1)