Chiyuan Zhang
Chiyuan Zhang
@henrikmarklund Depending on what you want to do. If you want to evaluate the generalization performance under the situation where the underlying data distribution has some probability of generating random...
`M` is the ground metric matrix, which should be defined beforehand according to your prior knowledge of the label space (i.e. how similar label a is to label b). Both...
I'm not sure if I follow your notation. Basically, `M` is `k x k` shape, where `M[i, j]` is the distance between class `i` and class `j`. The distance depend...
@rNMF Sorry, Mocha.jl is currently not compatible with Julia v1.0 yet.
@Sinansi Thanks! I'm not personally planning to work on this. But the project is open source, and anybody is welcomed to contribute or fork it if interested in. :)
Hi @Marsxia , which version of Julia are you using? Mocha is probably not compatible with Julia v1.0 yet.
@Marsxia Mocha.jl currently works with Julia 0.6. I will try to update it when I have time, meanwhile, you could try out [KNet.jl](https://github.com/denizyuret/Knet.jl) which seem to be quite up-to-date with...
What platform are you using? openmp is not generally available on Mac.
Maybe you can try to remove the `-fopenmp` option.
Is the out of memory error from cpu memory or gpu memory? Gpu memory is separated from cpu memory and is typically much smaller.