-
In the recent releases of Lux, I have found a worsened performance on some small NNs.
Here is a MWE
```
using BenchmarkTools
using Lux
using Random
rng = Xoshiro(2)
model = Chain(Dense(…
-
I stumbled across this repository, and while the approach seems interesting, actually the benchmark compares apple-to-oranges because the pure Python version is way too slow than what is expected. The…
-
I want to implement accessibility for screen readers in Ren'Py. This is different from self-voicing; instead of sending text directly to a speech synthesizer, this will make information about the cont…
-
Hi,
I'm trying out this implementation of a [Lux VAE ](https://gist.github.com/jowch/b1ca0526525d57ba30b64c4f1e21d0c7) and find a problem `Lux.testmode`. When I apply `Lux.testmode` to the encoder n…
rkube updated
2 months ago
-
Hey all! For those following along with the series on YouTube, I hope you've been enjoying it thus far! In the latest episode (Ep 11), we introduced multithreading into our code base by using `std::fo…
-
Blocker:
- [ ] ~~Zerocopy v0.8 — https://github.com/google/zerocopy/issues/671~~
Planned breaking changes for rand 0.9 are:
- [x] #1154
- [x] Make distributions in `rand` use `Result` (#1195, #1…
-
Hello,
I want to compute A*A^T where a is a matrix of polynomial elements like that
```julia
using Nemo
n, m = 2, 2
R, A, B = polynomial_ring(GF(101),:A=>(1:n, 1:m), :B=>(1:n, 1:m))
A * tran…
-
Won't get to it now, but it'll probably be useful at some point to have
- `InfRandTridiagonal`
- `InfRandSymTridiagonal`
- `InfRandBidiagonal`
with a LazyBandedMatrices extension
-
This issue is to provide a minimal example of neural network training with Lux to hopefully make it easier for developers to work toward making it viable. It probably isn't news to anyone here that t…
-
Hi there,
First of all thanks for this nice package. I had a problem when I tried to use the function `Stewart` to generate unitary matrices in my simulation though. The function rests in the file …