# tensorflow/hub

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

Repository: https://github.com/tensorflow/hub
Canonical: https://ross.abutalabs.com/products/tensorflow-hub
Homepage: https://tensorflow.org/hub
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensorflow, machine-learning, transfer-learning, embeddings, image-classification, python, ml
Last push: 2025-01-17T12:09:41+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 2, release rhythm 8, longevity 100
- inputs: {"age_days": 3096, "days_push": 593, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3523, forks 1641 (observed 2026-08-28T04:08:08.022495+00:00)

## What it is
TensorFlow Hub is a Python library for reusing parts of trained TensorFlow models (SavedModels) for transfer learning, wrapping them as Keras layers or loading them directly. The model repository itself has moved to Kaggle Models, and the library remains supported for downloading and loading those models.

## Use cases
- fine-tune pretrained models like BERT for text classification
- extract embeddings from text or images with a few lines of code
- reuse a Faster R-CNN model for object detection
- do transfer learning on image classifiers
- load SavedModels from tfhub.dev or Kaggle Models into Keras
- run image style transfer with a pretrained model

## When to choose
- you are already in the TensorFlow/Keras ecosystem and want pretrained models for transfer learning
- you need to load legacy tfhub.dev or Kaggle Models assets without rewriting code
- you want quick embeddings or fine-tuning with minimal code

## When to avoid
- you are starting a new project and can use Kaggle Models or Hugging Face directly
- you work in PyTorch or JAX rather than TensorFlow
- you need unmigrated tfhub.dev assets, which were deleted in March 2024

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, sdk
- domain: machine-learning, deep-learning, large-language-models, computer-vision
- platform: python, cross-platform
- tags: transfer-learning, tensorflow, pretrained-models, embeddings, model-repository, keras, fine-tuning, natural-language-processing

## Member repositories
- tensorflow/hub (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:08.022495+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:35:11.924828+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/hub (fetched 2026-08-28T04:08:08.022495+00:00, sha 418b6ecf3bb1)
  - homepage: https://tensorflow.org/hub (fetched 2026-08-29T09:29:25.816862+00:00, sha f0ec3a920090)
  - site_page: https://www.tensorflow.org/install (fetched 2026-08-29T09:29:25.819819+00:00, sha 584a762da891)
  - site_page: https://www.tensorflow.org/tfx/api_docs (fetched 2026-08-29T09:29:25.822927+00:00, sha 6977825696fe)
  - site_page: https://www.tensorflow.org/about (fetched 2026-08-29T09:29:25.826131+00:00, sha 817250744d91)
  - site_page: https://www.tensorflow.org/about/case-studies (fetched 2026-08-29T09:29:25.827650+00:00, sha e6701029eec0)
  - site_page: https://www.tensorflow.org/hub/api_docs/python/hub (fetched 2026-08-29T09:29:25.830342+00:00, sha 19f10d15ec06)
  - site_page: https://www.tensorflow.org/about/bib (fetched 2026-08-29T09:29:25.832660+00:00, sha 5ca8943386b9)
  - site_page: https://www.tensorflow.org/community/contribute (fetched 2026-08-29T09:29:25.824636+00:00, sha 77d394fa76e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.