onnx/tensorflow-onnx

Health v2 · maintenance only

Adoption not part of the score

2553 stars · 471 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning cli developer-tools machine-learning deep-learning developer-tools windows python cli model-conversion onnx tensorflow keras tflite tensorflowjs model-export interoperability linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="onnx/tensorflow-onnx")