liaohaofu
commented
4 years ago Hi, it is likely caused by the incorrect version of Pytorch. I didn't try my code with newer versions. So there might be unknown issues. Can you switch back to older (say using conda environment) version as noted in my installation requirement and see if that fixes it?
On Mon, Jun 8, 2020, 4:50 AM strive160 notifications@github.com wrote:
I ran your code, but this problem occurred, because It was ok when I ran it before. I recently installed a new environment, I wonder whether the current pytorch version does not fit your code or what Here's the problem RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 256, 4, 4]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/liaohaofu/adn/issues/10, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACJYGDGR3I2NGWDZP2RSUK3RVTF7XANCNFSM4NYKSVPQ .
I ran your code, but this problem occurred, because It was ok when I ran it before. I recently installed a new environment, I wonder whether the current pytorch version does not fit your code or what Here's the problem RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 256, 4, 4]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!