andevellicus

Feature Request: Instance Normalization

1

Would be nice to have. Computes the mean and variance for each each `W×H×1×1` slice and shifts them to have a new mean and variance Ref: https://arxiv.org/abs/1607.08022 Flux implementation: https://github.com/FluxML/Flux.jl/blob/2b1ba184d1a58c37543f4561413cddb2de594289/src/layers/normalise.jl#L249-L276

OneWayANOVATest seems to differ with different group sizes

1

I'm a bit of a stats noob so I'm not sure if this is expected behavior or not, but when using GLM's ftest to do ANOVA calculations, and HypothesisTests OneWayANOVATest,...

3D Upsampling

15

## Description Currently MXNet does not support upsampling on 5D tensors (3D images). There is more and more work being done in the medical field where 3D images are very...

# Feature Request Please provide a short description of your feature request here. E.g.: Would like to see an endpoint for faction warfare VP leaderboards per militia. ## Use case...

Julia 1.5 and 1.4 [1902f260] Knet v1.4.0 [e09e3f5a] KnetLayers v0.2.0 Probably to do with the recent changes in Knet.... ``` ERROR: LoadError: LoadError: UndefVarError: BNMoments not defined Stacktrace: [1] top-level...

Support for 3D convolutions (5DKnetArrays)

2

Hi, Great work so far, this is super helpful! I do a lot of work with 3D images, and I know KNet supports 5D arrays. How difficult would it be...

Feature request: 3D conv

1

Right now does not seem to support 3D convolutions. I tried to convert my model with a bunch of conv3D layers and I get ` ERROR: LoadError: "expected output_padding to...