awesome-semantic-segmentation-pytorch icon indicating copy to clipboard operation
awesome-semantic-segmentation-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon Tramac

dfa_net

Open wshj2020 opened this issue 4 years ago • 2 comments

I have met a question, I used dfa to train my own dataset,and it proformed well training, but worse in evaluating. why? Then my input are negative, is this normal? thank you ~

wshj2020 avatar May 14 '20 02:05 wshj2020

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [4, 8, 256, 256]], which is output 0 of ReluBackward1, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True)

wxk2008 avatar Jul 06 '20 07:07 wxk2008