Implementation of BasicTAD #2638
Open
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
2. support NMW 3. update README.md
Codecov ReportPatch has no changes to coverable lines.
📢 Thoughts on this report? Let us know!. |
|
Excellent job! Could you please push these commits to dev-1.x branch first? Thank you! |
|
@Dai-Wenxun I changed the branch for merging to |
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Outdated suggestions cannot be applied.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.
Motivation
Implement BasicTAD.
BasicTAD's main contribution is not in inventing complex modules, but in utilizing a modular architecture for temporal action detection tasks. As a result, the implementation of BasicTAD can mostly be achieved through code adapted from mmdetection.
While this project does not aim to replicate the original work's high performance, it does aim to implement its workflow.
Modification
Add a new project named basic_tad
Notes
I am only able to train the model in a basic setting due to my limited computing resources. This includes low spatial-temporal resolution, simple test augmentation, and evaluation on THUMOS14 only.
The current code needs to be cleaned up and the anchor-free version of BasicTAD is still in progress. Before proceeding with future work, may I please confirm your suggestion regarding this project?