CUDA out of memory about paperrobot HOT 7 CLOSED

@rzhangpku Thank you for your interest in our work. I think maybe you can change the batch_size to 40 by append --batch_size 40 or smaller and uncomment line 254.

from paperrobot.

@rzhangpku You can drop me an email if you still have this problem

from paperrobot.

As you say, I change the batch_size to 30 by append --batch_size 30 and uncomment line 254 in the train.py, then the problem is solved.
Thanks a lot for your quick and kind reply.

from paperrobot.

Hope you enjoy the experiments and have a good weekend!

from paperrobot.

Your work "PaperRobot" is very excellent and impressive! Have a nice weekend!

from paperrobot.

I have same question, but i can not solve it by decreasing batch_size.

from paperrobot.

@ClaireZTH Maybe you can further decrease batch size or choose a server with large GPU memory

from paperrobot.