Data

Tools

Indexes

Applications

Experiments

Open Source Science

bgnn-trait-segmentation

https://github.com/hdr-bgnn/bgnn-trait-segmentation

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 (3.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: hdr-bgnn
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 13.1 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 2
  • Open Issues: 2
  • Releases: 6
Created about 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

BGNN-trait-segmentation

PyTorch implementation of Fish trait segmentation model. This segmentation model is based on pretrained model using the segementation models torch Then the model is fine tune on fish image in order to identify (segment) the different traits. Trait list : + 'background' + 'dorsalfin' + 'adiposfin' + 'caudalfin' + 'analfin' + 'pelvicfin' + 'pectoralfin' + 'head' + 'eye' + 'caudalfinray' + 'altfinray' + 'trunk'

Requirements:

  • Python (>=3.6)
  • PyTorch
  • segmentationmodelspytorch
  • albumentations
  • Numpy
  • CV2
  • Matplotlib
  • Pillow
  • Seaborn
  • Pylab
  • Pandas

Source File

Run the singlemodeltraining.ipynb notebook for training.

Owner

  • Name: Biology Guided Neural Networks
  • Login: hdr-bgnn
  • Kind: organization

Citation (CITATION.cff) 

cff-version: 1.0.0
date-released: "2022-09-22"
abstract: "PyTorch implementation of Fish trait segmentation model. This segmentation model is based on pretrained model using the segementation models torch Then the model is fine tune on fish image in order to identify (segment) the different traits."
authors:
  - family-names: Maruf
    given-names: "M."
    orcid: "https://orcid.org/0000-0003-0637-1753"
  - family-names: Karpatne
    given-names: Anuj
    orcid: "https://orcid.org/0000-0003-1647-3534"
identifiers:
  - description: "Snapshot of BGNN-trait-segmentation."
    type: doi
    value: 10.57967/hf/0832
keywords:
  - "imageomics"
  - "image"
  - "segmentation"
license: MIT
repository-code: "https://github.com/hdr-bgnn/BGNN-trait-segmentation"
title: "BGNN trait segmentation"
version: 0.0.6

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • efficientnet-pytorch ==0.6.3
  • matplotlib *
  • pillow *
  • pretrainedmodels ==0.7.4
  • timm ==0.4.12
  • torchvision >=0.5.0
  • tqdm *
.github/workflows/deploy-image.yml actions
  • actions/checkout v2 composite
  • docker/build-push-action ad44023a93711e3deb337508980b4b5e9bcdc5dc composite
  • docker/login-action f054a8b539a109f9f41c372932f1ae047eff08c9 composite
  • docker/metadata-action 98669ae865ea3cffbcbaa878cf57c20bbf1c6c38 composite
Segment_mini/Dockerfile docker
  • ghcr.io/imageomics/dataverse-access 0.0.3 build
  • ubuntu 20.04 build