Data

Tools

Indexes

Applications

Experiments

Open Source Science

sam-clai

This is a repository for training and using the Segment Anything Model 2 for 3D images of granular materials.

https://github.com/theoortendahl/sam-clai

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

This is a repository for training and using the Segment Anything Model 2 for 3D images of granular materials.

Basic Info
  • Host: GitHub
  • Owner: theoortendahl
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 18.6 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 9 months ago · Last pushed 9 months ago
Metadata Files
Readme License Citation

README.md

SAM-clAI

This is a repository for training and using the Segment Anything Model 2 for 3D images of granular materials.

Instructions for running SAM 2

  1. The Segment Anything Model 2 is a prerequisite for this repository. Please follow the instructions here: https://github.com/facebookresearch/sam2/blob/main/README.md

  2. The necessary code for running SAM in this repository is found in run_sam.py. This file should be placed in "sam2/". ( not "sam2/sam2/").

  3. One folder containing each frame of the 3D image (in jpg-format) and a second folder containing input points (csv-file with 'X' and 'Y' column for each slice) should be placed in "sam2/notebooks/".

  4. cd to the first "sam2/" folder and run "python run_sam.py"

Instructions for training SAM 2

For training, the TRAIN.py folder should be placed in "sam2/training/".

Acknowledgments

This repository is heavily dependent on the main Segment Anything Model 2 repository: https://github.com/facebookresearch/sam2

TRAIN.py is adapted from the following github repository: https://github.com/sagieppel/fine-tune-trainsegmentanything2in60linesofcode

Owner

  • Login: theoortendahl
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Örtendahl"
  given-names: "Theo"
title: "Deep learning-based methods for segmentation and labelling of clay"
version: 1
date-released: 2025-06-05
url: "https://github.com/theoortendahl/SAM-clAI"

GitHub Events

Total
  • Push event: 5
  • Create event: 2
Last Year
  • Push event: 5
  • Create event: 2