Data

Tools

Indexes

Applications

Experiments

Open Source Science

yaltai

You Actually Look Twice At it

https://github.com/ponteineptique/yaltai

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
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.0%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

You Actually Look Twice At it

Basic Info
  • Host: GitHub
  • Owner: PonteIneptique
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 7.1 MB
Statistics
  • Stars: 35
  • Watchers: 5
  • Forks: 2
  • Open Issues: 7
  • Releases: 2
Created almost 4 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

YALTAi

You Actually Look Twice At it

This provides an adapter for Kraken to use YOLOv8 (1.0.0 update; use previous version to reuse YOLOv5 models) Object Detection routine.

This tool can be used for both segmenting and conversion of models.

Routine

Instal

bash pip install YALTAi

Training

Convert (and split optionally) your data

```bash

Keeps .1 data in the validation set and convert all alto into YOLOv5 format

Keeps the segmonto information up to the regions

yaltai convert alto-to-yolo PATH/TO/ALTOorPAGE/*.xml my-dataset --shuffle .1 --segmonto region ```

And then train YOLO

bash yolo task=detect mode=train model=yolov8n.pt data=my-dataset/config.yml epochs=100 plots=True device=0 batch=8 imgsz=960

Predicting

YALTAi has the same CLI interface as Kraken, so:

  • You can use base BLLA model for line or provide yours with -i model.mlmodel
  • Use a GPU (--device cuda:0) or a CPU (--device cpu)
  • Apply on batch (*.jpg)

```bash

Retrieve the best.pt after the training

It should be in runs/train/exp[NUMBER]/weights/best.pt

And then annotate your new data with the same CLI API as Kraken !

yaltai kraken --device cuda:0 -I "*.jpg" --suffix ".xml" segment --yolo runs/train/exp5/weights/best.pt ```

Metrics

The metrics produced from various libraries never gives the same mAP or Precision. I tried

  • object-detection-metrics==0.4
  • mapCalc
  • mean-average-precision which ended up being the chosen one (cleanest in terms of how I can access info)

and of course I compared with YOLOv5 raw results. Nothing worked the same. And the library YOLOv5 derives its metrics from is uninstallable through pip.

Owner

  • Name: Thibault Clérice
  • Login: PonteIneptique
  • Kind: user
  • Location: Chantilly, France
  • Company: PSL ENS - Lattice

Simply working on stuff.

Citation (CITATION.CFF) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: 'YALTAi: You Actually Look Twice At it'
message: "If you use this software, please cite both the article from preferred-citation and the software itself."
type: software
authors:
  - given-names: Thibault
    family-names: Clérice
    email: thibault.clerice@inria.fr
    affiliation: Inria
    orcid: 'https://orcid.org/0000-0003-1852-9204'
identifiers:
  - type: swh
    value: 'swh:1:snp:d9ca209ae2271537ff57d3748c8a76c49fd6222b'
  - type: other
    value: 'https://enc.hal.science/hal-03723208v3'
    description: Paper
repository-code: 'https://github.com/PonteIneptique/yaltai'
url: 'https://pypi.org/project/YALTAi/'
license: GPL-3.0
version: 1.0.0
date-released: '2023-01-01'
preferred-citation:
  authors:
    - family-names: Clérice
      given-names: Thibault
  title: "You Actually Look Twice At it (YALTAi): using an object detection approach instead of region segmentation within the Kraken engine"
  type: article
  volume-title: 'Historical Documents and automatic text recognition'
  journal: "Journal of Data Mining & Digital Humanities"
  doi:  'doi.org/10.46298/jdmdh.9806'
  date-published: "2023-12-01"

GitHub Events

Total
  • Issues event: 3
  • Watch event: 4
  • Delete event: 4
  • Issue comment event: 12
  • Push event: 5
  • Pull request event: 4
  • Fork event: 1
  • Create event: 2
Last Year
  • Issues event: 3
  • Watch event: 4
  • Delete event: 4
  • Issue comment event: 12
  • Push event: 5
  • Pull request event: 4
  • Fork event: 1
  • Create event: 2

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 53
  • Total Committers: 3
  • Avg Commits per committer: 17.667
  • Development Distribution Score (DDS): 0.057
Past Year
  • Commits: 12
  • Committers: 1
  • Avg Commits per committer: 12.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Thibault Clérice l****e@g****m 50
Thibault Clérice c****t@a****t 2
rohanchn c****1@g****m 1
Committer Domains (Top 20 + Academic)
algorythme.net: 1

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 21
  • Total pull requests: 8
  • Average time to close issues: 3 months
  • Average time to close pull requests: about 16 hours
  • Total issue authors: 9
  • Total pull request authors: 4
  • Average comments per issue: 6.52
  • Average comments per pull request: 0.88
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 4
  • Pull requests: 5
  • Average time to close issues: 16 days
  • Average time to close pull requests: about 16 hours
  • Issue authors: 3
  • Pull request authors: 2
  • Average comments per issue: 17.0
  • Average comments per pull request: 0.4
  • Merged pull requests: 3
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • rohanchn (5)
  • gabays (4)
  • PonteIneptique (3)
  • johnlockejrr (2)
  • pkzli (2)
  • PaulineJac (1)
  • trishaoconnor (1)
  • sven-nm (1)
Pull Request Authors
  • PonteIneptique (7)
  • mary-lev (2)
  • rohanchn (1)
  • Jean-Baptiste-Camps (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 285 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 21
  • Total maintainers: 1
pypi.org: yaltai

You Actually Look Twice At it, YOLOv5-Kraken adapter for region detection

  • Versions: 21
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 285 Last month
Rankings
Dependent packages count: 6.6%
Downloads: 15.5%
Stargazers count: 16.6%
Average: 20.0%
Forks count: 30.5%
Dependent repos count: 30.6%
Maintainers (1)
ponteineptique
Last synced: 8 months ago

Dependencies

requirements.txt pypi
  • click >=8.0.4
  • kraken >=4.1.2,<5.0.0
  • mean-average-precision ==2021.4.26.0
  • protobuf <3.20
  • tabulate *
  • torch <=1.11.0
  • torchvision *
  • yolov5 *
setup.py pypi