median-research-group/LibMTL

A PyTorch Library for Multi-Task Learning

57
/ 100
Established

LibMTL helps machine learning engineers and researchers streamline projects that require training a single model to perform multiple related tasks simultaneously. It takes in datasets for several tasks and produces a unified model that can handle them all, often improving efficiency and performance compared to training separate models. This is ideal for those working with deep learning models in various research or application domains.

2,531 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to train a single deep learning model to efficiently solve multiple, related prediction or classification problems at once.

Not ideal if your tasks are completely unrelated or if you prefer to build each model from scratch without leveraging existing multi-task learning frameworks.

deep-learning-research machine-learning-engineering multi-task-optimization model-training artificial-intelligence
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

2,531

Forks

232

Language

Python

License

MIT

Last pushed

May 14, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/median-research-group/LibMTL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.