If you want the converted model is compatible with certain ONNX version, please specify the target_opset parameter on invoking convert function, and the following Keras converter example code shows how it works.
keras-onnx converts models in ONNX format which can be then used to compute predictions with the backend of your choice. However, there exists a way to automatically check every converter with onnxruntime, onnxruntime-gpu. Every converter is tested with this backend.
keras-onnx converts models from scikit-learn. It was initially part of onnxmltools which can still be used to convert models for xgboost and libsvm. Other converters can be found on github/onnx, torch.onnx, ONNX-MXNet API, Microsoft.ML.Onnx…
It is licensed with MIT License.