What you’re asking for is literally impossible.
A neural network is basically nothing more than a set of weights. If one word makes a weight go up by 0.0001 and then another word makes it go down by 0.0001, and you do that billions of times for billions of weights, how do you determine what in the data created those weights? Every single thing that’s in the training data had some kind of effect on everything else.
It’s like combining billions of buckets of water together in a pool and then taking out 1 cup from that and trying to figure out which buckets contributed to that cup. It doesn’t make any sense.
There is also FreshTomato if your router has Broadcom wifi chipset like mine does.
Yeah I had to double check as well. It actually does elaborate.
“AMDGPU PRO OpenCL - used because Mesa OpenCL is not fully complete. Proprietary component only for Polaris GPUs. The onward GPUs use the open ROCm OpenCL.”
So for anything newer than the RX 500 series (anything after 2017) it doesn’t matter for OpenCL it seems.
From what I can gather the OpenCL stack used to be proprietary, but they decided to open source it when ROCm came along. So the Pro driver used to be more important and now it’s really only necessary for AMF since the Vulkan and OpenGL portions are straight up worse than mesa.
You are looking for GOverlay with vkBasalt. You can configure various filters and I am pretty sure it’s on a per-game basis.
Proton and the Steam Runtime bundle a bunch of different libraries so they all play nice together and are consistent across everybody’s machines. There are the obvious things like DXVK and VKD3D, but the Steam Runtime includes basically all of the system files that affect games. It’s not quite the same thing but for the sake of simplicity think of it like running in a virtual machine. The Steam Runtime is using libraries from Debian. It is the same concept as docker if you know how that works.
Lutris on the other hand lets you select DXVK and VKD3D versions independently of the wine version, and uses your system’s actual libraries rather than the standardized ones. If you’re wondering why running Proton inside of Lutris is not working it’s because Lutris is missing the Steam Runtime. It’s searching for a container that doesn’t exist so it can’t even start in the first place.
Proton isn’t meant to be run outside of Steam at all. If you are running games in Lutris you need to use the “lutris-GE-Proton8-14” you can find in the Lutris wine version manager. There is actually a huge bold disclaimer about that on the proton-ge-custom repo I linked in my last comment. Proton (and Steam) bundles a bunch of libraries together while Lutris uses whatever versions your system has installed.
Proton is Valve’s version of wine running inside a container specifically made for Steam, while Lutris is only using wine.
And the versions being used by Lutris and the version being used by Steam are not the exact same thing. If you use GloriousEggroll for example there is the proton-ge-custom repo for Proton, which is the one Steam uses, and the wine-ge-custom repo that Lutris uses.
I’m not even sure that the latest “GE-Proton8-14” and “Wine-GE-Proton8-14” are actually equivalent to each other. They were released two weeks apart and might be based on slightly different wine and/or dxvk versions since they are using whatever the bleeding edge git commits are, rather than actual stable releases (i.e. using commit #ABCD1234 instead of release version 1.2.3)
Sorry, I misinterpreted what you meant. You said “any AI models” so I thought you were talking about the model itself should somehow know where the data came from. Obviously the companies training the models can catalog their data sources.
But besides that, if you work on AI you should know better than anyone that removing training data is counter to the goal of fixing overfitting. You need more data to make the model more generalized. All you’d be doing is making it more likely to reproduce existing material because it has less to work off of. That’s worse for everyone.