-
### Branch
master branch (0.24 or other 0.x version)
### Describe the feature
I want to develop a training strategy like model averaging, for example, after every 10 iterations, the parameters of t…
-
Hi, @anayebi , I am a newbie in keras, I want to do sequence classification (e.g., 2 classes, each element in the sequence is a 2d matrix or image) just like the first architecture in fig 3 in this ar…
-
For some recent ne256 runs on Perlmutter I accidentally used `Averaging Type: Instant` for my monthly output stream and it led to this error message:
```
800:
800: FAIL:
800: mm>=1 && mm=1 && …
-
Now that IterativeImputation() has been added, it may be the right moment to discuss addition of yet another advanced imputation strategy: multiple imputation. The core idea is to aggregate across sev…
-
I tried to replicate the results from your benchmarks using docker gpu with this docker image nvidia/cuda:12.6.1-cudnn-devel-ubuntu22.04 and nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04. After I instal…
-
Hello,
Thank you for this great piece of software :) Extremely useful.
I was wondering **how to get fully reproducible results (or averaged/repeated results)**, maybe by:
1. Using fix seeds for…
-
I am trying to reproduce the geometry diagrams on the front page and was hoping for more details on how they are generated. I have tried the following procedure:
- Take a set of embeddings
- Compu…
ixxie updated
4 years ago
-
### Operating System
Mac OS
### (Linux only) Distribution
_No response_
### (Linux only) Desktop Environment
_No response_
### (Linux Only) Display Server
None
### Installation…
-
Functions that would make sense to be somewhere else include the following. Ideally, they would find a home in another, more related package. If they won't logically move to another related package …
-
BARN models currently only return a single ensemble from the posterior distribution (i.e. a single MCMC replicate). BART, however, allows returning an average over *multiple* MCMC iterations. Doing …