This repository has been archived by the owner on Nov 29, 2023. It is now read-only.
Add Swapping out Conv2D for CoordConv/AntiAliased Conv2D in models #60
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
…s, and RUNet/Attention Unet models Makes it easy to swap between standard Conv2D layers, CoordConv layers, and soon, Anti-aliased Conv2D layers
Only change ones that have a stride of 2, like in the directions in the repo
|
As the antialiased layer needs some more changes around it to work, and isn't a drop in replacement like CoordConv, the antialiased layers are more spread throughout the codebase, and have to be implemented on a per model/layer thing. |
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Outdated suggestions cannot be applied.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.
Relates to #27 makes it easy to swap out the different Conv2D methods for all conv layers in different models