# tensorflow/skflow

Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

Repository: https://github.com/tensorflow/skflow
Canonical: https://ross.abutalabs.com/products/skflow
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2021-08-30T20:14:47+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3941, "days_push": 1829, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3168, forks 436 (observed 2026-08-28T04:07:47.314519+00:00)

## What it is
A simplified Scikit Learn-style interface for TensorFlow deep learning, providing estimators for neural networks. It was merged into TensorFlow's contrib/learn module and this repository is no longer maintained.

## Use cases
- train neural networks with a scikit-learn fit/predict API
- build deep learning classifiers and regressors in TensorFlow
- experiment with TensorFlow models using familiar sklearn-style code

## When to choose
- studying the historical origins of tf.contrib.learn / TF Learn
- maintaining legacy code that depends on the skflow package

## When to avoid
- starting any new project - it was merged into TensorFlow and later removed
- using modern TensorFlow versions where contrib/learn no longer exists
- needing maintained deep learning estimator APIs - use tf.keras or scikit-learn instead

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: scikit-learn, tensorflow, deprecated, merged-upstream

## Member repositories
- tensorflow/skflow (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.314519+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 2026-08-29T18:45:31.549998+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/skflow (fetched 2026-08-28T04:07:47.314519+00:00, sha ed03a7964fe2)
  - registry_pypi: https://pypi.org/pypi/skflow/json (fetched 2026-08-29T09:39:42.557986+00:00, sha 2312d29c9db3)
- Data as of 2026-08-30T08:39:29.467469+00:00.