tflite2onnx 0.2.0

Convert TensorFlow Lite models to ONNX models

Converting TensorFlow Lite models to ONNX

tflite2onnx converts TensorFlow Lite (TFLite) models (*.tflite) to ONNX models (*.onnx).

This project is under early stage of development, contributions are welcome.

Usage

If you'd like to convert a TensorFlow model (*.pb or SavedModel whatever) to ONNX, try tf2onnx. Or, you can firstly convert it to TFLite (*.tflite), and then convert the TFLite model to ONNX.

Install via pip pip install tflite2onnx. After installation, you may either try either.

Python interface

import tflite2onnx

tflite_path = '/path/to/original/tflite/model'
onnx_path = '/path/to/save/converted/onnx/model'

tflite2onnx.convert(tflite_path, onnx_path)

tflite2onnx now supports explicit layout, check the test example.

Command line

tflite2onnx /path/to/original/tflite/model /path/to/save/converted/onnx/model

Contributing

Any contribution is welcome to this tool.

• If you think something is wrong, report bugs.
• If some operators are not supported yet, you may request new operator.
• It would be great if you can help to enable new operators, please join us with How to enable new operator.
• Feel free to open discussions if you have any great idea to improve this tool.

Resources

• Release note.
• PyPI page.
• GitHub page.
• TensorFlow Lite converter.

License

Apache License Version 2.0.