How many number of photo needed for it to be good at learning/training ?
and what / which type of Trainer that is good E.G : Dlight - Dfaker - Original ... something like that
and also other thing is.... how to change directory of the faceswap or what ever it is... because when i train something ... it uses my C: Disk (Partition) instead of D: , where i installed the Faceswap and Anaconda at... and my C: Disk is keep lowering in capacity everytime i want to train instead of D: ?....
thats the problem... all of the models... including Faces Input A / B - Model Dir - Timelapse input and output , even the anaconda and faceswap installation is on D: .. like all of them ... but i can clearly see when ever Train.. my C: Partition just keep Dropping from 100 GB to 90 and depend on how long it train.. it goes to 80... and i can even check it to make sure where it is by using Large File Finder and after that i tried full uninstall and tryin to find every last bit of folder and install it again but to no avail ... it keep dropping
I haven't seen this before, It won't be anything specifically Faceswap, but some of the upstream libraries we use may be creating temporary files on the c drive?