Burf/ModelSoups

ModelSoups for Tensorflow2 and Torch

33
/ 100
Emerging

This tool helps machine learning practitioners combine multiple existing machine learning models into a single, more accurate model without increasing the time it takes for the model to make predictions. You provide several trained models, and it intelligently merges their internal components to produce one refined model. This is for data scientists or ML engineers looking to boost the performance of their image recognition, natural language processing, or other deep learning applications.

No commits in the last 6 months.

Use this if you have several fine-tuned deep learning models for the same task and want to improve their collective accuracy without making your system slower.

Not ideal if you are starting from scratch and don't already have multiple pre-trained or fine-tuned deep learning models.

deep-learning model-optimization machine-learning-engineering model-ensembling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

50

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 27, 2022

Commits (30d)

0

Get this data via API

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

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