# onnx/onnx-tensorflow

Tensorflow Backend for ONNX

Repository: https://github.com/onnx/onnx-tensorflow
Canonical: https://ross.abutalabs.com/products/onnx-tensorflow
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-neural-networks, deep-learning, tensorflow, onnx
Last push: 2026-08-23T06:56:02+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 3254, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- 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 1326, forks 299 (observed 2026-08-28T04:04:22.727036+00:00)

## What it is
A Python library and CLI that converts ONNX machine learning models into TensorFlow models so they can be executed with TensorFlow. It is the ONNX-to-TensorFlow counterpart of tf2onnx.

## Use cases
- convert onnx model to tensorflow
- run onnx models with tensorflow backend
- port pytorch-exported onnx models into tensorflow
- cli tool to convert .onnx files to saved tensorflow models
- infer onnx models using tensorflow runtime

## When to choose
- you have an ONNX model and need to run or integrate it in a TensorFlow pipeline
- you need programmatic or CLI-based ONNX-to-TensorFlow conversion

## When to avoid
- you need actively maintained tooling - the repo is deprecated and unmaintained
- you want to convert TensorFlow models to ONNX (use tf2onnx instead)
- you target TensorFlow Lite or newer TF2 workflows with ongoing support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, compiler, cli
- domain: deep-learning, machine-learning, developer-tools
- platform: python, cross-platform
- tags: onnx, tensorflow, model-conversion, model-portability, deprecated

## Member repositories
- onnx/onnx-tensorflow (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.727036+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 2026-08-30T04:46:24.010368+00:00, confidence not recorded.
  - readme: https://github.com/onnx/onnx-tensorflow (fetched 2026-08-28T04:04:22.727036+00:00, sha fe3730829c7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.