Skip to content

OpenNMT-py v0.5.0

Compare
Choose a tag to compare
@vince62s vince62s released this 24 Oct 19:17
· 799 commits to master since this release
32af678

Ability to reset the optimizer when using -train_from

-reset_optim = ['none', 'all', 'states', 'keep_states']
none: default behavior as before
all: reset the optimizer !! steps start at zero again.
states: reset only states, keep all other parameters from checkpoint
keep_states: keep current states from checkpoint, but allow to change parameters (learning_rate for instance)

Bug fixes.
Tested with Pytorch 1.0RC works fine.