Data

Tools

Indexes

Applications

Experiments

Open Source Science

train-scripts

This repository contrains scripts and files related to ML training for the QUMIA project

https://github.com/qumia/train-scripts

Science Score: 49.0%

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
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.7%) to scientific vocabulary

Keywords

ai neuromuscular ultrasound
Last synced: 6 months ago · JSON representation

Repository

This repository contrains scripts and files related to ML training for the QUMIA project

Basic Info
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 1
Topics
ai neuromuscular ultrasound
Created over 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

DOI

These are a bunch of files used for training models for the QUMIA project.

Contents

These are the most important files:

  • run-session.sh - the script that sets up a training session on the HPC environment: labelling, committing, copying and adding a train job to the job queue.

  • train-job.sh / validate-job.sh - the SLURM jobs.

  • train.py - the main script that sets up all the elements and performs the training and validation. It is actually based on an Python notebook (used for development purposes, but not committed due to potential data leaks) that is converted to train.py as part of the run-session.sh script.

  • qumia_*.py - the actual code that is used by the train script, thematically spread over several modules.

  • convert-notebook.sh - script that is used to convert Pyhon notebooks to stand-alone scripts.

  • data-prep/ - directory with preprocessing code. These are also based on Python notebooks, but converted to scripts (see train.py).

Owner

  • Name: QUMIA
  • Login: QUMIA
  • Kind: organization

GitHub Events

Total
  • Release event: 1
  • Push event: 10
  • Create event: 1
Last Year
  • Release event: 1
  • Push event: 10
  • Create event: 1

Dependencies

requirements.txt pypi
  • Pillow ==10.0.1
  • albumentations ==1.3.1
  • ipykernel ==6.25.2
  • ipython ==8.16.1
  • matplotlib ==3.8.0
  • numpy ==1.26.0
  • opencv-python ==4.8.1.78
  • pandas ==2.1.1
  • python-dotenv ==1.0.0
  • scikit-learn ==1.3.1
  • scipy ==1.11.3
  • torch ==1.13.0
  • torchsummary ==1.5.1
  • torchvision ==0.14.0
  • tqdm ==4.66.1
  • wandb ==0.16.0