machinelearningnuremberg/QuickTune

[ICLR2024] Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

28
/ 100
Experimental

Quick-Tune helps machine learning practitioners efficiently choose the best pre-trained model and fine-tuning strategy for a new image classification task. You provide your image dataset, and it outputs recommendations for the best model architecture and how to fine-tune it. This is designed for researchers or MLOps engineers who need to quickly adapt existing models to specific image classification challenges.

No commits in the last 6 months.

Use this if you are working with image classification and need to rapidly identify optimal pre-trained models and fine-tuning configurations to improve performance on a new dataset.

Not ideal if your task is not image classification or if you are looking for a complete end-to-end model training and deployment solution.

Image Classification Machine Learning Research Model Selection Deep Learning Fine-tuning MLOps
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

33

Forks

4

Language

Python

License

Last pushed

Sep 07, 2025

Commits (30d)

0

Get this data via API

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

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