Mikoto10032/AutomaticWeightedLoss

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

46
/ 100
Emerging

This tool helps machine learning engineers and researchers manage multiple loss functions when training deep learning models for tasks like scene geometry and semantics. It takes individual loss values from different tasks as input and automatically assigns learnable weights to each, combining them into a single, optimized sum. This is for professionals building complex AI models that perform several related predictions simultaneously.

647 stars. No commits in the last 6 months.

Use this if you are building a multi-task deep learning model and need an automated, robust way to balance the contributions of different loss functions during training without manual tuning.

Not ideal if your project involves single-task learning or if you prefer to manually set and adjust loss weights.

deep-learning multi-task-learning neural-network-training computer-vision machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

647

Forks

88

Language

Python

License

Apache-2.0

Last pushed

Jun 20, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Mikoto10032/AutomaticWeightedLoss"

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