[Feature Request]: Support for Real, Imag, Complex

onnx / tensorflow-onnx

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Apache License 2.0

2.29k stars 432 forks source link

[Feature Request]: Support for Real, Imag, Complex #1959

Open lminer opened 2 years ago

lminer commented 2 years ago

It would be great to get support for Real, Imag, and Complex. Anybody working with audio data has to deal with complex inputs and this is very difficult without support for these ops.

fatcat-z commented 2 years ago

Could you please provide some public models which are impacted now?

lminer commented 2 years ago

Most, current audio source separation models are impacted by this limitation as they use an audio signal representation called "complex as channels", where the real and imaginary parts of the complex spectrogram are extracted and stacked along the channels dimension. Some examples are: Demucs MDXNet LaSaft DCUNet