RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [100, 6, 32]], which is output 0 of ReluBackward0, 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).

Question

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [100, 6, 32]], which is output 0 of ReluBackward0, 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).

BeitaNine opened this issue 2 years ago · 1 comments

Hi，Thanks your answer
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [100, 6, 32]], which is output 0 of ReluBackward0, 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).

Answer 1 · 2022-11-04T03:38:59.000Z

THE QUESTION HAS SOLVED ,USE TORCH VERSION ==1.8.0