Skip to content
This repository has been archived by the owner on Dec 1, 2021. It is now read-only.

add triangular learning rate #74

Closed
tkng opened this issue Dec 12, 2018 · 2 comments
Closed

add triangular learning rate #74

tkng opened this issue Dec 12, 2018 · 2 comments
Labels
enhancement New feature or request good first issue Good for newcomers

Comments

@tkng
Copy link
Contributor

tkng commented Dec 12, 2018

Recently I read some articles that uses triangular learning rate or cyclical learning rate.

I tested on my local environment, triangular learning rate tends to achieve better accuracy than current 2 steps-decay, even if I add 1 epoch warm up manually.

On the other hand, we found a problem with current learning rate schedulings, we cannot train wider_face object detection network. More precisely, we can train, but the mAP is not good (roughly 40%, which is worse compared to hand tuned 55% mAP.)

I'd like to have some experiment around triangular learning rate and add best configuration as our choice. But unfortunately, I don't have enough time, so I just leave this comment 😢

@ruimashita ruimashita added enhancement New feature or request good first issue Good for newcomers labels Feb 14, 2019
@a-hanamoto
Copy link

@tkng Do you need help?

@tkng
Copy link
Contributor Author

tkng commented May 25, 2020

@a-hanamoto thanks!

Recently I'm using cosine learning rate decay, now I'm feeling that it's better than triangualr learning rate. Hence, I just close this issue.

@tkng tkng closed this as completed May 25, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
enhancement New feature or request good first issue Good for newcomers
Projects
None yet
Development

No branches or pull requests

3 participants