add I-JEPA pretrained weight for ViT #1846
Merged
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
seefun
changed the title
|
The documentation is not available anymore as the PR was closed or merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Add weights from: https://github.com/facebookresearch/ijepa , a strong self-sup pretraining method from FAIR / Lecun's team. (Similar to MAE and other MIM methods in some aspects)
It seems that only the weight of the vit backbone is provided (without the classifier's weight).
Alos support dynamic input size, but only test in ViT-H. Due to the small DRAM of my work pc, I did no check whether ViT-G pretrained is correctly loaded. May need help verifying the correctness of weight loading.