Open Simplex-AP opened 8 years ago
Depends on #39 and see my work in #16. The ability to define custom loss functions requires layers written in python and is what inspired me to work on it. I have plans to work on this but it will need to wait till julia v0.5
Another option which might be easier to implement (though involves quite a lot refactoring but not technically difficult) is the new module system in the mxnet python side. See dmlc/mxnet#1868 for example. With the new module system, a hybrid symbolic and imperative module can be used. The computation graph is built using symbolic nodes, while the loss function is written directly in Python.
Unfortunately, I have no estimate of timeline when I would be able to find enough time to port that to Julia side. Contributions are very welcome of course!
There is a discussion In R branch of MXNet. They propose to use MakeLoss function. I've tried to implement their solution in julia:
Well, generally speaking it works, but it looks ugly. it would be nice, if anyone with deep knowledge of MXNet could help.
There are few questions:
The python version of MXNet has the capability to define custom loss functions, but this is missing from the Julia version. Are there any plans to add it?