Andrei Zhabinski
Andrei Zhabinski
High-level API for model training similar to PyTorch Lightning. One advantage over Python is that we don't need a separate module type to add methods to a model class (e.g....
- [x] Add [Documenter](https://github.com/JuliaDocs/Documenter.jl) - [ ] Write down all node types
From dfdx/Yota.jl#93: ```julia A = rand(100, 100) x = rand(100) rrule(*, x', A, x) # ==> nothing ``` It's possible to binarize the operation on the AD engine side, but...
Does it make sense to put functional forms of [BatchNorm and Dropout](https://github.com/FluxML/Flux.jl/blob/86097e76fdaa149b2caf815d5404c77d16c4f754/src/layers/normalisation.jl) into NNlib so that other packages could simply import them from here?
Given the increasing importance of NNlib in the ML ecosystem, I believe it's time to add automatic benchmarks. This PR is based on the amazing PkgBenchmark.jl and [config from ProximalOperators.jl](https://github.com/kul-forbes/ProximalOperators.jl/tree/master/benchmark)....
```julia import Random import NNlib import NNlib: DenseConvDims Random.seed!(42); function ngradient(f, xs::AbstractArray...) grads = zero.(xs) for (x, Δ) in zip(xs, grads), i in 1:length(x) δ = sqrt(eps()) tmp = x[i]...
I'm trying to understand the meaning and usage of [this signature](https://github.com/FluxML/NNlib.jl/blob/master/src/conv.jl#L41) in the new convolution interface: ``` conv!(y::AbstractArray{T,3}, x::AbstractArray{T,3}, w::AbstractArray{T,3} ```` `w` here should have at least 4 parameters: 1....
How do we deal with datasets that are too large to be read into an `Array`? Something of 5-50Gb, for example. Are there any tools for it or earlier discussion?...