SirBitesalot

If we implement this we need to keep in mind that some Nodes are dependent on others. Like Inventory and StatsSystem

As a first step it is now possible to copy nodes that have no childnodes. This sadly prevents copying over for inventory for example. We will continue to expand this...

Exports of unknown nodes as binary blob are supported now and can be checked out with this release: https://github.com/WolvenKit/CyberCAT/releases/tag/v0.0.6-alpha Issue can stay open for now as this feature is not...

Hello thank you for this PR. Unfortunately this still causes errors on my end when loading a 1.5 save game. I would assume there are many more changes in other...

1. What error are you getting that prevents you from generating the dataset whith the included Alphabet file? 2. For the Matching segments. Are you using "combine clips" in advanced...

I just ran a test and on my end I get: Size: 0 hours, 31 minutes Total clips: 255 Maybe something went wrong during setup? Normally it should not be...

@Schokodrache As for the error with disappering umlauts. Please convert the file to utf-8 encoding and try again. @BenAAndrew Maybe this needs to be added as some hint or something....

What GPU are you using? I remember that some GPUs had some weird issue with some other ML stuff.

its an issue with 1660/1660TI I think https://github.com/pytorch/pytorch/issues/58123 You could try to use another version of CUDNN. Or try to run the app from source see if removing .half() can...

I think the model should be fine as only the inference uses .half() and it produces a normal graph.