search

avisingh599 / visual-qa

[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering
https://avisingh599.github.io/deeplearning/visual-qa/
MIT License
481 stars 186 forks source link

dumpText.py returns with 'Killed' #16

Open aniemerg opened 8 years ago

aniemerg commented 8 years ago

I installed Visual-qa in a Docker container run on a Mac. While running get_started.sh, I ran into trouble with

python dumpText.py -split train -answers modal

Running that line separately, it was exiting prematurely with the simple message "Killed". I worked line by line through the code and qa = json.load(open(annFile, 'r')) appears to be the source of the problems. My best guess is that JSON is attempting to load the entire training annotations file into memory fails because of its size.

avisingh599 commented 8 years ago

I am not familiar with Mac, but when I work on Linux I usually increase my swap when I run into memory issues. I have tested the software on 8GB RAM, and about ~15GB Swap (if I remember correctly).

If that does not have work out, then you may have to break the training data into multiple files, and load them one by one while training.

tczhangzhi commented 6 years ago

You can follow these steps to run it. Avisingh599 is right. You need to expend your swap~