-
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…
-
Hi, I'm using Optimization.jl in my package: [DJUICE.jl](https://github.com/DJ4Earth/DJUICE.jl) to optimize a cost function. The example is [here](https://github.com/DJ4Earth/DJUICE.jl/blob/test_opt…
-
I'm not sure if I should be filing this here or in CUDA, but doing temporary `@allowscalar`s lead to errors when taking a gradient.
MWE:
```
using Zygote, CUDA
CUDA.allowscalar(false)
f(x) = CUDA…
-
I've run into an issue where I want to compute the gradient of an implicit function that itself depends on another implicit function. I can do the operation successfully with `FowardDiff`, however I …
-
````
julia> kernel() = 0
kernel (generic function with 1 method)
julia> GPUCompiler.@override method_table kernel() = 1
julia> native_code_llvm(kernel, Tuple{})
; @ REPL[1]:1 within `kernel`…
-
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()
…
-
I've implemented `rrules` for the QR factorization and the pullbacks calculate the same as FiniteDifferences:
https://gist.github.com/rkube/ccdd21b8009e5be281f3870a0caec47c
```
function ChainRule…
rkube updated
3 years ago
-
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),…
-
I supposed that the CNOT gate should be available without including `qelib1.inc`. But I still got an error when using `@code_qasm`, even if I include `qelib1.inc`.
```julia
julia> using YaoCompil…
-
Hi,
I'm using a Dict to memoize outputs from Flux layers to avoid recomputing stuff when output from one layer is input to more than one other layer.
With Julia 1.3.0, Flux 0.10 and Zygote 0.4.1…