This repository has been archived by the owner on Mar 11, 2021. It is now read-only.
Swish #799
Merged
Swish #799
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
|
From the paper: "For training Swish networks, we found that slightly lowering the learning rate used to train ReLU networks works well." It would have been nice if they provided actual numbers here :/ |
tommadams
approved these changes
Apr 1, 2019
|
LGTM |
|
@tommadams Per personal communication slight is 20-30% on the initial learning rate (which is followed by a 10x cut at the first decay) |
amj
approved these changes
Apr 1, 2019
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Based on https://arxiv.org/pdf/1710.05941.pdf
This needs to be rebased after #798