This repository has been archived by the owner on Nov 1, 2024. It is now read-only.
Add VitConv configs; use batch-first implementation #166
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
facebook-github-bot
added
the
CLA Signed
Tete-Xiao
force-pushed
the
vitconfigs_os
branch
2 times, most recently
from
8b6d064 to
1c3ccbd
Compare
|
@Tete-Xiao has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: The update modifies length-first implementation of MultiheadAttention to batch-first implementation. PyTorch >= 1.9 required.
Tete-Xiao
force-pushed
the
vitconfigs_os
branch
from
1c3ccbd to
5b23abd
Compare
|
@Tete-Xiao has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
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Outdated suggestions cannot be applied.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.
Summary:
The update modifies length-first implementation of
MultiheadAttention to batch-first implementation.
Baseline configs of ViTConv models are added.
PyTorch >= 1.9 required.