Mikoto10032/AutomaticWeightedLoss
Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning
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.
Stars
647
Forks
88
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
zeiss-microscopy/OAD
Collection of tools and scripts useful to automate microscopy workflows in ZEN Blue using Python...
median-research-group/LibMTL
A PyTorch Library for Multi-Task Learning
qdrant/quaterion
Blazing fast framework for fine-tuning similarity learning models
lucidrains/PoPE-pytorch
Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) -...
MR-HosseinzadehTaher/BenchmarkTransferLearning
Official PyTorch Implementation and Pre-trained Models for Benchmarking Transfer Learning for...