chainer
chainer copied to clipboard
Support complex types
Currently Chainer assumes integers and floating point numbers. Now CuPy supports complex numbers. It's time to support complex numbers in Chainer.
- [ ] Support complex numbers in gradient check
- [ ] Support complex numbers in various functions
I'm curious about this, do you already have use-cases in mind or is that to broaden the capabilities of Chainer? I see your related ongoing PR, does that target the reproduction of a specific paper?
Yes. Some research papers use complex numbers or FFT. And i think it can be applied for speech processing. I want to improve capability of Chainer.
- https://arxiv.org/abs/1511.06464
- https://arxiv.org/abs/1611.00035
- http://www.aclweb.org/anthology/D16-1044
Understood. Thanks for the papers, I didn't know about the last two, seems very interesting! Looking forward to use it in Chainer 👍
You should definitely look into https://arxiv.org/pdf/1701.00392.pdf as well.
Thank you for a link!! Please thumb up this issue if you guys need this feature.
Should Chainer support "complex32" whose real/imag part is float16
? It seems NumPy hasn't yet support "complex32".
IMO, no, especially for the first implementation.
I would like to work on this. Could anyone guide me with the process? Thanks!