tflite2onnx
converts TensorFlow Lite (TFLite) models (*.tflite
) to ONNX models (*.onnx
),
with data layout and quantization semantic properly handled (check the introduction blog for detail).
If you'd like to convert a TensorFlow model (frozen graph
*.pb
,SavedModel
or whatever) to ONNX, trytf2onnx
. Or, you can firstly convert it to a TFLite (*.tflite
) model, and then convert the TFLite model to ONNX.
It's significant to understand the use cases of tflite2onnx
, which helps us
to decide how to shape tflite2onnx
- what features we take as first priority for example.
Please help to provide some input in this issue
Support of this tool is by best effort - we have very limited resouce, i.e. basically off time effort by the maintainers. So we encourage you to deep dive into your issue and then discuss with us to figure out a solution. Please join to improve!
Install via pip pip install tflite2onnx
.
Or install from source to get latest features:
- Download the source code:
git clone https://github.com/jackwish/tflite2onnx.git
- Build the package:
${tflite2onnx}/tools/build-wheel.sh
- Install the built package:
pip install assets/dist/tflite2onnx-*.whl
Or you can just add the code tree to your $PYTHONPATH
.
(Command line tool is not avaiable in this mode.)
export PYTHONPATH=$(pwd):${PYTHONPATH}
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.
tflite2onnx /path/to/original/tflite/model /path/to/save/converted/onnx/model
- If something seems wrong to you, report bugs.
- If some operators are not supported yet, you may request a new operator.
- It would be great if you can help to enable new operators, please join us with How to enable a new operator.
- Feel free to open any other related discussions.
Check contribution guide for more.
- Introduction blog - the background, design and implementation
- Release note
- FAQ
- Contribution guide
- Supported operators (Onging status issue)
- How to enable a new operator
- Data layout semantic
Apache License Version 2.0.