# tensorflow/models

Models and examples built with TensorFlow

Repository: https://github.com/tensorflow/models
Canonical: https://ross.abutalabs.com/products/models
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-08-25T21:25:59+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 58, longevity 100
- inputs: {"age_days": 3863, "days_push": 8, "days_rel": 203, "gap_med": 81.0, "n_releases_24m": 5}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 77652, forks 44878 (observed 2026-08-28T04:12:21.651953+00:00)

## What it is
The TensorFlow Model Garden is a repository of official and community implementations of state-of-the-art machine learning models built with TensorFlow 2. It includes optimized official models, research model code, and the Orbit library for custom distributed training loops.

## Use cases
- train state-of-the-art image classification models in TensorFlow
- fine-tune BERT or other NLP models with TensorFlow 2
- find reference implementations of research papers in TensorFlow
- build custom distributed training loops on GPU or TPU
- get reproducible training logs for vision and NLP models

## When to choose
- you use TensorFlow and want well-maintained, optimized SOTA model implementations
- you need reference code for reproducing research models
- you want a pip-installable library of official TensorFlow models

## When to avoid
- you work primarily in PyTorch or JAX
- you need production serving infrastructure rather than model code
- you need a specific model not covered by the garden

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training, computer-vision, nlp
- domain: machine-learning, deep-learning, computer-vision
- platform: python, cross-platform
- tags: tensorflow, model-garden, sota-models, pretrained-models, training-loops, research-models, natural-language-processing, gpu

## Member repositories
- tensorflow/models (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.651953+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 2026-08-29T16:14:16.668180+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/models (fetched 2026-08-28T04:12:21.651953+00:00, sha a456d4d4436c)
- Data as of 2026-08-30T08:39:29.467469+00:00.