SkBlaz

@yonatankarni it seems there is an issue with `/FW/src/block_relu.rs` (not sure if you meant we have a look after re-opening, if not please ignore this)

Hey @zz242msu, thanks for noticing this. Indeed, the file seems to be missing. Note however that there are many other edgelists/relevant datasets present here: https://github.com/SkBlaz/py3plex/tree/master/datasets. Feel free to modify the...

Hey, thanks for noticing this. If your fix for undir in general, feel free to PR, will check dir case asap (unless you get to it first of course -...

@jsnagai added you as a collaborator, should you take steps before I get to that

Appreciate it! On Wed, 31 May 2023, 11:38 James Nagai, ***@***.***> wrote: > tysm SkBlaz, im a bit busy with other projects on my Ph.D. but I can try >...

@Alex1235321 -> could you please retry with py3plex==0.95 -> current builds most likely failed due to nx's breaking changes that are a separate issue alltogether

Hi! Either downgrade your numpy, or, if possible, open a PR with the suggested change so this is fixed also for others. Thanks! On Fri, 29 Mar 2024, 05:44 nico-dangelo,...

The simplest way is via autoregression; simply represent each instance with values for past n time points - these are your features. Value at time t is the target. Of...

@APCunha sorry for the late reply, you could retrieve attention vectors after each time period - it would show incremental change in attention in time ..

Hi! Glad you were able to build on top, great work so far. Based on e.g., https://arxiv.org/pdf/1705.09792.pdf paper, cross-entropy loss is for sure one option. Alternatively, one would imagine loss...