The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Branch: main

gh/HDCharles/1/base

gh/HDCharles/1/head

gh/HDCharles/1/orig

main

minidemo

Branches Tags

${ item.name }

Create tag ${ searchTerm }

Create branch ${ searchTerm }

from 'main'

${ noResults }

segment-anything/segment_anything

History

Eric Mintun 567662b0fd Fix incorrect shape in ResizeLongestSide.apply_image_torch.		2 years ago
..
modeling	Corrected docstring typo of class PatchEmbed	2 years ago
utils	Fix incorrect shape in ResizeLongestSide.apply_image_torch.	2 years ago
__init__.py	Initial commit	2 years ago
automatic_mask_generator.py	Lint.	2 years ago
build_sam.py	remove direct call to build_sam()	2 years ago
predictor.py	Fix mypy thinking output of SamPredictor.predict is a tensor.	2 years ago