错误:
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [100, 1]], which is output 0 of TanhBackward0, 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).
场景:在训练pytorch网络的时候的报错。
解决方法:
mu *= 2
改为:
mu = mu * 2
Original: https://www.cnblogs.com/Twobox/p/16736031.html
Author: Wei_Xiong
Title: 记一次BUG,RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
原创文章受到原创版权保护。转载请注明出处:https://www.johngo689.com/566194/
转载文章受原作者版权保护。转载请注明原作者出处!