machinelearningnuremberg/QuickTune
[ICLR2024] Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
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.
Stars
33
Forks
4
Language
Python
License
—
Category
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.
Higher-rated alternatives
limix-ldm-ai/LimiX
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence...
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
google-research/plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets...
YalaLab/pillar-finetune
Finetuning framework for Pillar medical imaging models.
thuml/LogME
Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML...