-
There are some ongoing efforts to make Oceananigans.jl composable with Enzyme.jl (an AD package).
This is currently spearheaded by DJ4Earth:
https://dj4earth.github.io/
With a project update her…
-
I was wondering if it where possible to develop an new booster, that instead of taking the mean of values inside a leaf instead fitted a linear function. In cases of lower numbers a features its possi…
-
Hi,
I am currently toying with the idea to implement multi sample Monte Carlo objectives such as the importance weighted auto encoder [1] and VIMCO [2] in Edward. For that purpose, I browsed the code…
-
# Description
For my thesis project, I'm applying a novel Polyak-averaging approach to various reinforcement learning algorithms; the approach uses natural-gradient descent in order to estimate the…
-
I wanted to freeze the first two layers of the network. Based on [this](http://pytorch.org/docs/master/notes/autograd.html?#excluding-requires-grad)
I wrote a code to freeze the first two layers like…
-
Hi Xuanyi, I meet a confusing problem while I'm using SWMM2PEST2.1. It is the output data doesn't change after calibration, see the picture below. Hope that you can help me out of this problem, thanks…
-
Hello. I am currently using Mac M1. And running the following code. It shows the error from the pybind11 ``` ROL.Algorithm("Line Search", params)```. Does anyone know why``` "Line search"``` be recog…
-
### Describe the bug
I want to match the level of motion blur between two images, so I am using Kornia's optimization ability to optimize the parameters of the kornia.filters.motion_blur function. Sp…
-
### Feature description
I think this feature is a fairly simple one. The implementation is not exactly clear to me as the whole package is really centered around the use of current functions.
In …
mleot updated
4 months ago
-
In the medium-long term, it makes little sense to continue to support a tape-based AD package when there is excellent work going on elsewhere in the Julia community; see [Capstan](https://github.com/J…