tensorflow/hub

A library for transfer learning by reusing parts of TensorFlow models.

51
/ 100
Established

This library helps machine learning engineers and researchers accelerate the development of new models by reusing pre-trained components. Instead of building models from scratch, you can take existing TensorFlow models or parts of them from Kaggle Models, combine them with your own data, and fine-tune them for specific tasks. This drastically reduces the time and resources needed to develop high-performing machine learning solutions.

3,527 stars. No commits in the last 6 months.

Use this if you are a machine learning practitioner looking to leverage existing robust models to quickly build new solutions or improve current ones without extensive training from the ground up.

Not ideal if you are a beginner looking for a simple, no-code solution for applying machine learning models, as this tool requires familiarity with TensorFlow and Python programming.

machine-learning-engineering model-development transfer-learning deep-learning AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

3,527

Forks

1,649

Language

Python

License

Apache-2.0

Last pushed

Jan 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/tensorflow/hub"

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