problem with model S2VTModel

xiadingZ / video-caption.pytorch

pytorch implementation of video captioning

MIT License

401 stars 130 forks source link

problem with model S2VTModel #13

Closed qy-feng closed 6 years ago

qy-feng commented 6 years ago

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation This error occurs when I use S2VTModel, but everything works well with S2VTAttModel. As I started with S2VTModel and want to fix this bug, but failed. Do you have any idea?

ParitoshParmar commented 6 years ago

@qy-feng , try commenting out lines 51, 52 (self.rnn1.flatten_parameters(); self.rnn2.flatten_parameters()) in S2VTModel. It should resolve your issue.

qy-feng commented 6 years ago

Perfectly solved. Thanks!