Fixes #109
Merged
Fixes #109
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
About saving the best model, I noticed that you use the WER to determine whether the model is getting better or worse. Shouldn't we be using the loss on the validation set instead? In most of my experiments, I've noticed that the WER might converge to a value but the loss starts increasing after several epochs. |
|
@SiddGururani problem is I see that the validation loss diverges after a while, which doesn't usually reflect how well the WER/CER is... I was doing an average over the 2 but I thought WER was representative enough! |
mit456
reviewed
Jul 7, 2017
| @@ -372,6 +376,13 @@ def main(): | |||
| optimizer.load_state_dict(optim_state) | |||
| print('Learning rate annealed to: {lr:.6f}'.format(lr=optim_state['param_groups'][0]['lr'])) | |||
|
|
|||
| if best_wer is None or best_wer > wer: | |||
| print("Found better validated model, saving to %s" % args.final_model_path) | |||
There was a problem hiding this comment.
Shouldn't it be args.model_path? @SeanNaren
There was a problem hiding this comment.
Thanks for that, fixed here
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Formatted decode script, added dels to benchmark and updated train to save best model