NormalizingFlows.jl
NormalizingFlows.jl copied to clipboard
TuringLang
This pull request changes the compat entry for the `ADTypes` package from `0.1` to `0.1, 1`. This keeps the compat entries for earlier versions. Note: I have not tested your...
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "github-actions[bot] avatar"){kind=avatar}
This pull request changes the compat entry for the `ADTypes` package from `0.1` to `0.1, 0.2`. This keeps the compat entries for earlier versions. Note: I have not tested your...
It seems overloading an external package in an extension doesn't work (which is probably for the better), so atm the CUDA tests are failing. But if we move the overloads...
as per issue #15 - [ ] implement a set of famous NFs illustrating the usage of `NormalizingFlows.jl` + `Bijectors.jl` (a tentative list) - [x] planar and radial flow -...
- [ ] implement a set of famous NFs illustrating the usage of `NormalizingFlows.jl` + `Bijectors.jl` (a tentative list) - [x] planar and radial flow - [x] [Real NVP](https://arxiv.org/abs/1605.08803) -...
as per https://github.com/TuringLang/NormalizingFlows.jl/pull/8#discussion_r1283544729
- [x] synthetic examples that are challenging to sample - [x] Banana - [x] Cross distribution - [x] warped Gaussian - [x] neal's funnel
```julia using CUDA using LinearAlgebra using FunctionChains using Bijectors using Flux T = Float32 q0 = MvNormal(ones(T, 2)) Distributions._rand!(rng, q0_g, xx) ts = reduce(∘, [f32(Bijectors.PlanarLayer(2)) for _ in 1:2]) flow...