paarthneekhara / text-to-image

Text to image synthesis using thought vectors

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Memory usage in data processing step

guillefix opened this issue · comments

Hi,
I've followed the setup instructions. However, when I do python data_loader.py --data_set="flowers", my memory usage seems to go up and up, while the time for the processing of each image caption also goes up and up. Eventually I ran out of memory and it crashes..

Any idea why this may be?

I'm using Ubuntu 16, and have 12 Gb of RAM, and a GTX1080Ti
I have never used Theano (which skipthoughts uses), but I do have it installed