報(bào)錯：

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [544, 768]], which is output 0 of ViewBackward, 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).
?

解決方法：

報(bào)錯原因是因?yàn)槲以诖罱ňW(wǎng)絡(luò)模型時，殘差相加的代碼是這樣寫的： x += y

但是在pytorch中這樣寫會有問題， 改成: x = x+y就好了

總結(jié)

以上是生活随笔為你收集整理的RuntimeError: one of the variables needed for gradient computation has been modified by an inplace的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。