Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/atelierarith/segrcdb.jl

Unofficial Julia implementation of SegRCDB.jl

https://github.com/atelierarith/segrcdb.jl

Science Score: 26.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (17.1%) to scientific vocabulary

Keywords

dataset dataset-generation fdsl julia-language machine-learning-algorithms
Last synced: 5 months ago · JSON representation

Repository

Unofficial Julia implementation of SegRCDB.jl

Basic Info
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
dataset dataset-generation fdsl julia-language machine-learning-algorithms
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

SegRCDB Build Status Stable Dev

Description

  • This is an unofficial Julia implementation of SegRCDB(SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning) that is proposed by Shinoda, Risa and Hayamizu, Ryo and Nakashima, Kodai and Inoue, Nakamasa and Yokota, Rio and Kataoka, Hirokatsu.
  • The official implementation uses Python and it assumes that we are supposed to use high performance computer with more than 40 cores. See this line of code. It doesn't provide have a progress bar feature like tqdm, so it's impossible to predict when it will finish and how much storage we need. It seems they are reusing their source code in several projects that are well-known in FDSL/RCDB. Some lines are hard to interpret as the variable names remain unchanged, and from a software quality perspective, this cannot be overlooked.
  • SegRCDB.jl is written in Julia, a high-performance programming language, so it is designed to address performance issues. The generate_dataset.jl script can run using multiple threads and includes a progress bar feature. On my 2019 Intel macOS laptop, it completes in under 5 minutes with 16-threads. Even with a single thread, it should finish within 15 minutes, so there's no need for concern. Currently M1 mode is only supported.

How to use

console git clone https://github.com/AtelierArith/SegRCDB.jl.git cd SegRCDB.jl julia --project=@. -e 'using Pkg; Pkg.instantiate()' julia --project=@. generate_params.jl julia --project=@. --threads auto generate_dataset.jl

This Julia package SegRCDB.jl behaves the same as the official implementation. Namely it will generate a directory named SegRCDB-dataset/param, SegRCDB-dataset/image and SegRCDB-dataset/mask.

⚠️ Note that it consumes 12G of storage.

Results

SegRCDB (generated by the Python-based original implementation.)

image

SegRCDB.jl (this repository)

image

image

Appendix

dockerand docker compose commands allow us to setup an environment and generating dataset easily:

console git clone https://github.com/AtelierArith/SegRCDB.jl.git cd SegRCDB.jl make && make test && make dataset

Owner

  • Name: AtelierArith
  • Login: AtelierArith
  • Kind: organization
  • Email: contact@atelier-arith.jp
  • Location: Japan

Enhance "Math meets Art"

GitHub Events

Total
  • Delete event: 3
  • Push event: 14
  • Pull request event: 6
  • Create event: 2
Last Year
  • Delete event: 3
  • Push event: 14
  • Pull request event: 6
  • Create event: 2

Committers

Last synced: 10 months ago

All Time
  • Total Commits: 30
  • Total Committers: 2
  • Avg Commits per committer: 15.0
  • Development Distribution Score (DDS): 0.4
Past Year
  • Commits: 8
  • Committers: 2
  • Avg Commits per committer: 4.0
  • Development Distribution Score (DDS): 0.125
Top Committers
Name Email Commits
Satoshi Terasaki t****h@g****m 18
CompatHelper Julia c****y@j****g 12
Committer Domains (Top 20 + Academic)
julialang.org: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 1
  • Total pull requests: 24
  • Average time to close issues: about 9 hours
  • Average time to close pull requests: 3 days
  • Total issue authors: 1
  • Total pull request authors: 2
  • Average comments per issue: 1.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 16
  • Bot issues: 0
  • Bot pull requests: 20
Past Year
  • Issues: 0
  • Pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: 38 minutes
  • Issue authors: 0
  • Pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 3
  • Bot issues: 0
  • Bot pull requests: 1
View more stats
Top Authors
Issue Authors
  • terasakisatoshi (1)
Pull Request Authors
  • github-actions[bot] (19)
  • terasakisatoshi (6)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

.github/workflows/CI.yml actions
  • actions/checkout v3 composite
  • julia-actions/cache v1 composite
  • julia-actions/julia-buildpkg v1 composite
  • julia-actions/julia-docdeploy v1 composite
  • julia-actions/julia-runtest v1 composite
  • julia-actions/setup-julia v1 composite
.github/workflows/CompatHelper.yml actions
.github/workflows/TagBot.yml actions
  • JuliaRegistries/TagBot v1 composite
Dockerfile docker
  • julia 1.9.3 build
docker-compose.yml docker
  • segrcdbjl latest