Skip to content

My implementation of SAM Med2D model based on its paper

Notifications You must be signed in to change notification settings

cheeyeo/SamMed2D_Custom

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SAM-Med2D

My own custom implementation of SAM-Med2D model from scratch using torch in order to learn how SAM model works.

SAM-Med2D uses a pre-trained SAM model with additional AdapterLayer added in the attention blocks to fine-tune the model to recognise segmentation maps from medical scans which are provided via bounding boxes or prompts via the prompt encoder.

( MORE ON MODEL ARCHITECTURE ETC )

It's still a work in progress with initial ImageEncoder model built and tests added.

About

My implementation of SAM Med2D model based on its paper

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages