search

dmlc / MXNet.jl

MXNet Julia Package - flexible and efficient deep learning in Julia
371 stars 70 forks source link

Variational Autoencoders - error function #103

Open int8 opened 8 years ago

int8 commented 8 years ago

Hello there,

I'm not sure if this is a proper place to ask such a question - if not, please guide me to a place where I can find some help.

Is it possible now to implement Variational Autoencoders in Julia using MXNet.jl ?

Cost/error function is composed of two components there - one is placed at the very end of computation graph which is probably possible to implement but the other cost function component is "attached" somewhere in the middle of the graph - (KL Divergence between parametrized Gaussian and Normal Distribution)

For details take a look at: http://arxiv.org/pdf/1606.05908v1.pdf (Figure 4 - right part of it)

Little bit more generic question could emerge here: Is it possible to have a computation graph that is not a chain (single path of computations) but more complex structure like the network for VAE ?

Thanks a lot,

iblislin commented 6 years ago

Hi @int8 , there is an example from upstream mxnet (in Python) https://github.com/apache/incubator-mxnet/tree/master/example/vae

A port of Julia version is welcome.