# onnx/tensorflow-onnx

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Repository: https://github.com/onnx/tensorflow-onnx
Canonical: https://ross.abutalabs.com/products/tensorflow-onnx
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: tensorflow, onnx, export, convert, keras, tflite, tensorflowjs, deep-learning
Last push: 2026-08-03T14:22:09+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 41, longevity 100
- inputs: {"age_days": 3095, "days_push": 30, "days_rel": 182, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2553, forks 471 (observed 2026-08-28T04:07:00.587312+00:00)

## What it is
tf2onnx is a tool that converts TensorFlow, Keras, TensorFlow.js, and TFLite models into the ONNX format via a command-line interface or Python API. It enables TensorFlow-trained models to run on ONNX-compatible runtimes and hardware.

## Use cases
- convert a trained TensorFlow model to ONNX for deployment with ONNX Runtime
- export Keras models to ONNX format
- convert TensorFlow Lite models to ONNX
- run TensorFlow models on hardware that only supports ONNX
- convert tensorflow.js models to ONNX
- migrate TensorFlow inference pipelines to ONNX runtimes

## When to choose
- you need to deploy TensorFlow or Keras models on ONNX-compatible runtimes or accelerators
- you want a CLI or Python API for batch model conversion
- you need to convert tflite or tfjs models to ONNX

## When to avoid
- your model uses TensorFlow ops not supported by ONNX mappings
- you need PyTorch or other framework model conversion
- you need actively maintained support for the latest TensorFlow versions, as the project is seeking a new maintainer

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, cli, developer-tools
- domain: machine-learning, deep-learning, developer-tools
- platform: windows, python, cli
- tags: model-conversion, onnx, tensorflow, keras, tflite, tensorflowjs, model-export, interoperability, linux, macos

## Member repositories
- onnx/tensorflow-onnx (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:00.587312+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 2026-08-30T02:23:47.264887+00:00, confidence not recorded.
  - readme: https://github.com/onnx/tensorflow-onnx (fetched 2026-08-28T04:07:00.587312+00:00, sha 1c1568cd8a51)
- Data as of 2026-08-30T08:39:29.467469+00:00.
