Segment Anything V2

napari-SAMV2

Napari plugin for segment anything version 2 model from meta. Plugin primarily useful for segmenting 3d volumetric data or 3d time series data.

Workflow step:
Image annotation
Image segmentation

Napari plugin to use segment anything version 2 models from Meta.

Plugin primarily made for segmenting 3d volumetric data or 3d time series data.


Installation

You can install napari-SAMV2 via pip:

pip install napari-SAMV2

Pre-requisite of samv2 installation needed:

git clone https://github.com/facebookresearch/segment-anything-2.git
cd segment-anything-2
pip install -e .

The plugin and installation tested with python 3.10 in conda environment with pytorch-cuda=12.1

If you are installing samv2 in a separate environment, you can follow the below tested env,

conda create -n samv2_env python=3.10
conda activate samv2_env
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
python -m pip install "napari[all]"

git clone https://github.com/facebookresearch/segment-anything-2.git
cd segment-anything-2
pip install -e .

pip install napari-SAMV2    

To install latest development version :

pip install git+https://github.com/Krishvraman/napari-SAMV2.git

Usage

Middle mouse click - positive point

Ctrl + Middle mouse click - negative point

Time Series Segmentation :

samv2_time_series_demo

Volume Segmentation :

samv2_volume_segmentation

Reference :

Example Data from in demo videos from, Cell tracking challenge - https://celltrackingchallenge.net/ FlyEM project - https://www.janelia.org/project-team/flyem/hemibrain

License

Distributed under the terms of the BSD-3 license, "napari-SAMV2" is free and open source software

Issues

If you encounter any problems, please file an issue along with a detailed description.

Version:

  • 0.0.4

Last updated:

  • 09 October 2024

First released:

  • 08 October 2024

License:

Supported data:

  • Information not submitted

Plugin type:

GitHub activity:

  • Stars: 1
  • Forks: 0
  • Issues + PRs: 0

Python versions supported:

Operating system:

Requirements:

  • numpy
  • magicgui
  • qtpy
  • scikit-image