TomXi | Qingyang Xi

Results 8 comments of TomXi | Qingyang Xi

Documenting some of the discussions that happened off-line: We want to support more options for bandwidth estimation. Currently, bandwidth estimation supports only a scalar input or `None` in which case...

Also crema... which I think is gonna be my use case. Why would this involve an api change?

Caveat about wrapping pre-trained embedding in general: If the model contains things like custom Keras layers that can’t be pickled directly, then the resulting pump object won’t be picklable, which...

Thanks for the review. Nothing on my end, I think it's ready.

The structural training idea is morphing, and probably be best to separate the Key Model to another project.

Thanks! Updated the readme.md and Zenodo page accordingly

Thanks! Updated the readme.md and Zenodo page accordingly

Just to add: This chord actually happened in our dataset. Here's the played chord as represented by tablature. ![a0](https://user-images.githubusercontent.com/6080581/39643427-bb75dc84-4fa2-11e8-910b-6d7cac696381.png) I feel like similar situations can arise pretty easily in Jazz,...