I am training a Machine Learning (Neural Network, "AI") model for epileptic seizure detection. An issue I have is that I have a lot more false alarm data than I do genuine seizure data, so I am using 'Data Augmentation' to make more seizure-like data.
Unfortunately when doing this using Python, it seems to eat huge amounts of memory. The 16GB on my computer is not enough, so I added more swap space using the following:
fallocate -l 16G /swapfile2
chmod 600 /swapfile2
mkswap /swapfile2
swapon /swapfile2
Check it is working with
swapon --show
or
free -h
