# google/prettytensor

Pretty Tensor: Fluent Networks in TensorFlow

Repository: https://github.com/google/prettytensor
Canonical: https://ross.abutalabs.com/products/prettytensor
Language: Python
License Family: other
Archived: true
Last push: 2020-05-17T17:37:00+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3957, "days_push": 2299, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1227, forks 142 (observed 2026-08-28T04:04:03.285446+00:00)

## What it is
Pretty Tensor is a Python library providing a fluent, chainable builder API on top of TensorFlow for defining multi-layer neural networks. It wraps Tensors so layers like fully_connected and softmax classifiers can be composed in a readable pipeline.

## Use cases
- build neural networks with a chainable API in TensorFlow
- define multi-layer perceptrons quickly
- wrap tensors to add layers fluently
- train classifiers with built-in softmax and loss helpers
- integrate custom TensorFlow ops into a layer chain

## When to choose
- you maintain legacy TensorFlow 1.x code that already uses Pretty Tensor
- you want a concise fluent syntax for defining small TF1 models

## When to avoid
- you use TensorFlow 2.x or Keras, which this library does not support
- you are starting a new deep learning project
- you need actively maintained or documented tooling

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: tensorflow, neural-networks, fluent-api, builder-pattern

## Member repositories
- google/prettytensor (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.285446+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 2026-08-30T06:15:15.484040+00:00, confidence not recorded.
  - readme: https://github.com/google/prettytensor (fetched 2026-08-28T04:04:03.285446+00:00, sha cc0f4e133263)
  - registry_pypi: https://pypi.org/pypi/prettytensor/json (fetched 2026-08-29T12:23:16.030959+00:00, sha 237dff4c38ab)
- Data as of 2026-08-30T08:39:29.467469+00:00.