You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I implemented my own version of LoRA for SAM2 which is similar to the version found for the original segment anything. Instead of targeting the queries and values for the regular attention blocks as did in SAM1, I targeted the MultiScaleBlock q and v. Are there any additional modifications that need to be made?
For instance, adding LoRA to image encoder?
The text was updated successfully, but these errors were encountered: