-
```julia
using Flux, Zygote
model = Dense(3,1)
grad_f(x) = gradient(x -> sum(model(x)),x)[1]
Zygote.jacobian(grad_f,rand(3))
ERROR: Can't differentiate foreigncall expression.
You might want t…
-
We are missing rules for `cov`, which makes Zygote sad because `cov` internally mutates arrays.
```julia
julia> using Zygote
julia> y = rand(2, 50)
2×50 Matrix{Float64}:
0.400221 0.162725 …
-
This was discussed on slack, but I've opened an issue here at @oscardssmith 's suggestion.
The issue is that type inference for the below example when using the `NativeInterpreter` (correctly) in…
-
I don't really know if this is a Cassette issue or a Julia issue, but the thing that's weirdest about it to me is that this big error gets thrown but it doesn't actually interrupt the function call. Y…
-
Zygote v0.6.41, Julia 1.7.3
MWE:
```julia
using Zygote
α, β = randn(2, 2), randn(2, 2)
g(v) = map(eachcol(v), eachcol(β)) do x, y
sum(x.*x.*y)
end |> sum
# this fails
…
-
Calling `StatsModels.fit` with a not yet seen formula seems to trigger pretty slow compilation, even if a structurally equivalent formula with different names _has_ been seen before. Triggering `fit` …
-
I am just copying from https://github.com/FluxML/Zygote.jl/issues/668. Not sure if this should be fixed here or in Zygote.
```julia
julia> using Zygote, ProgressMeter
julia> function train()
…
-
The second example from https://fluxml.ai/Flux.jl/stable/models/regularisation/ trips up Zygote if you try to compute the gradient:
```
m = Chain(
Dense(28^2, 128, relu),
Dense(128, 32, relu),…
-
When I move a BitArray to the gpu from within a gradient call, I get the following error.
```julia
using CUDA, Zygote
function f(a, b)
sum(a .* b)
end
a = rand(10, 10, 10)|>cu
b = rand(…
-
Hi, it seems that the `rrule` for `mean(f, x)` is not vectorized and thus does not place nicely with CUDA:
```julia
using Zygote, CUDA, Statistics
julia> gradient(y -> mean(x -> x.^2, y), CUDA.…