-
I am using Distances.jl for kernel functions, and have started looking into Zygote for some automatic differentiation.
However, for a parametrized distance like `WeightedSqEuclidean` this runs into …
-
An effort to create a very simple Decapode, to help simplify diagnosing autodiff through decapode issues.
This is a 1-D harmonic oscillator Decapode:
```
using Catlab
using Catlab.Graphics
using…
-
Hi,
The background is that in Encoder-Decoder model used for translation from "Attention Is All You Need" I desired to mask-out the padding in sentence passed to Encoder's MultiHeadAttention, but I…
mashu updated
3 months ago
-
I want to take gradient of a vectorized expression, however the adjoint of vmaterialize is not defined.
```
using Zygote
using LoopVectorization
foo(x) = sum(@avx tanh.(x))
x = rand(10, 10)
foo'…
-
Hi, `Coupling` currently has an issue with differentiation.
Here's a reproducible example.
```julia
using Bijectors
using Flux
using ProgressMeter
using StatsBase
using StatsPlots
using Turi…
-
LabelledArrays looks very promising to simplify model definitions. Unfortunately it seem largely incompatible with AD. Is there a good workaround?
```Julia
using LabelledArrays
import ForwardDiff
…
-
### Bug description
My device is a Chinese car multimedia with Android 9 x86. I can't patch any YouTube apk from a couple of months now, which forces me to use pre-patched revanced APKs as a workarou…
-
I wanted to try something simple with [SciMLSensitivity.jl](https://github.com/SciML/SciMLSensitivity.jl) to find the sensitivities of the solution to a `LinearProblem` with respect to parameters. How…
-
It seems that only ForwardDiff is supported for ADing sampling. Is it possible to implement rules for Zygote as well?
```
julia> ForwardDiff.derivative(x -> sum(rand(Normal(x, 10), 10)), 0.)
10.0…
-
1. make ``cam`` in ``project`` a
```
struct Camera{T}
rot :: SVector{3,T}
centre :: SVector{2,T}
radial :: SVector{2,T}
focal :: T
X0 : SVector{2,T}
```