Dilation for Fully Convolutional Networks #63
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
|
@lukemelas can you give this a look? |
|
Yes! Sorry for the delay. I will take a look and probably merge this weekend. |
|
@lukemelas just wanted to follow up because I've got some code I'm releasing soon which depends on this change and people will probably use the wrong version without this merged! |
|
@lukemelas I've updated the branch to match the current master, any chance you can merge this? |
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Outdated suggestions cannot be applied.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.
I've added
num_dilationto the global params and dilation to each mbconv block param to add support for dilation of stride 2 layers for use in Fully Convolutional Networks.This change should be backwards compatible and have no problem loading the existing models.