[WIP] Porting MViT architecture #6086
Closed
Conversation
This file contains hidden or 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
…general clean up.
24 tasks
datumbox
changed the title
|
superseded by #6105 which does a complete rewrite |
37 tasks
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Outdated suggestions cannot be applied.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.
This PR adds MViTv2 to TorchVision. It's based on @haooooooqi, @feichtenhofer and @lyttonhao 's work for migrating the original PyTorchVideo implementation.
It is an exploratory PR and the work is in progress. It's unclear if we will opt in for rewriting the implementation or continue refactoring based on the original. The equivalent diff is D36634383, exported to Github for easier testing on the CI. I'll update the PR and remove the draft status later to indicate it's open for reviews on styles, code structure etc.