search

Neuroglycerin / neukrill-net-work

NDSB competition repository for scripting, note taking and writing submissions.
MIT License
0 stars 0 forks source link

Training from pickled models #49

Closed gngdb closed 9 years ago

gngdb commented 9 years ago

We're wasting time training from bad initialisations (probably). Why not start with a high scoring initialisation? How this is specified in the YAML is described here.

We should have an example YAML file that can do this with our current best and hopefully we can then tune from there (increasing learning rate and decaying again?) and get a better score?

alinaselega commented 9 years ago

Giving a saved model in the yaml file to start training from now works. The example of how to do this is (for the time being) in alexnet_based_load_pkl.yaml.