FacT-Finetuning SAM #680
Closed
FacT-Finetuning SAM #680
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
…n script to include lora functionality
caroteu
commented
Sep 1, 2024
caroteu
commented
Sep 1, 2024
caroteu
commented
Sep 1, 2024
caroteu
commented
Sep 1, 2024
| @@ -79,6 +122,10 @@ def __init__( | |||
|
|
|||
| assert rank > 0 | |||
|
|
|||
| dim = model.image_encoder.blocks[0].attn.qkv.in_features | |||
| self.FacTu = nn.Linear(dim, rank, bias=False) | |||
There was a problem hiding this comment.
@anwai98 Do we need to add a condition here, so that these parameters are only initialized when FacT is used?
There was a problem hiding this comment.
Hmm, we definitely cannot hard-code them in the current location, would create a bit of a mess. While reviewing, Ill try to see how we can make it flexible upon the peft module.
|
I'll close this PR in favor of moving it to #682. |
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Outdated suggestions cannot be applied.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.
Implementation of FacT Finetuning method on SAM. @anwai98