PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
This tool helps machine learning engineers and researchers convert their trained AI models from the ONNX format into various other formats like TensorFlow, TFLite, Keras, or PyTorch. You provide an ONNX model file as input and receive a functionally equivalent model in your desired target framework. This is crucial for deploying models across different platforms or integrating them into diverse software environments.
931 stars. Used by 2 other packages. Actively maintained with 268 commits in the last 30 days. Available on PyPI.
Use this if you need to convert an ONNX model into TensorFlow, TFLite, Keras, or PyTorch formats for deployment or integration into different machine learning ecosystems.
Not ideal if you are specifically working with LiteRT Torch, as the project recommends using LiteRT Torch directly for that purpose.
Stars
931
Forks
97
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
268
Dependencies
20
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PINTO0309/onnx2tf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX
microsoft/onnxconverter-common
Common utilities for ONNX converters