-
It's that time of year again, and having done some work with Nvidia's new hardware sporting "TensorRT" cores, I thought it'd make a nice project to evaluate whether or not Accelerate programs would be…
-
There are many cases where one wants to modify a value in an array like `A[i, j] = f(A[i, j])`, If `A` is a `LinearSlow` array this would currently need two transformation between the Cartesian index …
-
First of all, keep up the great work! I think this library is awesome and I'd like to contribute one day.
I have a matrix `M` whose entries depend on one or more input parameters, and I am computin…
-
# Overview
Since a distributions has to be re-implemented here and the focus is on AD, I was wondering if it would be of any interested to add reparameterization to `Distribution`. In AD-context you …
-
朋友,我想复现你的代码,始终报错AttributeError:` 'tuple' object has no attribute 'layer',我想是keras或者tensorflow版本问题之类的,但是我的tensorflow==1.14.0,keras==2.2.4,keras_bert==0.69。
下面是python console:
Using TensorFlow backe…
-
Suppose I have a function
```julia
function pairwise(a)
ret = Matrix{eltype(a)}(undef, length(a), length(a))
for i in 1:(length(a)-1)
for j in (i+1):length(a)
ret[i, …
-
I saw https://github.com/SHI-Labs/NATTEN/issues/89
> As far as I know both FAv2 and xFormers' FMHA support 1-D sliding window attention with causal masking, so you probably can use them for now, bu…
-
Add beta coefficients (coefficients for standardized data) as a post-estimation results method.
API: return similar to t_test with params table, summary, summary_frame
Most likely this can inter…
-
@jasonmayes raises the question of [whether WebGPU exposes the right API surface needed to support ML frameworks interactions with GPUs](https://www.w3.org/2020/06/machine-learning-workshop/talks/oppo…
-
E.g.
``` c++
constexpr auto rng = view::iota(0, 10);
constexpr auto rng2 = view::iota(0) | view::take(10);
constexpr auto rng3 = rng | view::transform(square) | view::remove_if(odd);
```
should prob…