breizhn / DTLN

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
MIT License
585 stars 161 forks source link

can't convert same onnx by provided python file. #39

Open fmbao opened 3 years ago

fmbao commented 3 years ago

I convert onnx file by convert_weights_to_onnx.py. The onnx files converted is not sames onnx files provided

fmbao commented 3 years ago

I know why.... TF 2.1 can convert same. However, TF 2.3 can't convert same model.