Saber is a deep-learning based tool for information extraction in the biomedical domain. Pull requests are welcome! Note: this is a work in progress. Many things are broken, and the codebase is not stable.
The random seed is chosen with saber.constants.RANDOM_STATE (42 by default). This value is used to seed the random number generators of pythons random module, numpy, and torch.
This will allow us to run multiple trials with different random seeds and then average them.
coveralls
commented
5 years ago
Quick PR to fix all random seeds.
The random seed is chosen with
saber.constants.RANDOM_STATE(42by default). This value is used to seed the random number generators of pythonsrandommodule,numpy, andtorch.This will allow us to run multiple trials with different random seeds and then average them.