Todor Arnaudov

I also tried QSV again (OpenShot-v2.5.2-release-candidate-6915-f344214c-5487efb2-x86_64.exe) after not using it for a long time, I recently turned on the built-in Intel HD. I have used it in old versions (2.4.x...

Change make -j8 to make -j3 or -j2 or if it still doesn't complete: -j1. Watch the memory usage during the build with htop. If you add -B - it...

@Ali007788 Try the koide3's solution - it has just worked for me.

Maybe out of memory error? Try: make -j3 -B Or -j1 (number of threads, -B -rebuild, -d debug;) Watch the RAM usage with htop. BTW, that combination "make -j8" is...

It is a good idea, DFL serves as a restoration, it reconstructs the proper shapes, as it also usually "de-agifies" the faces, because the models average/smooth the featuers. I had...

@sokffa Yes. I just tried to fix it, I managed until the last cell which had some incompatibility, outdated/mismatched versions or so which I couldn't fix yet. I tried many...

Good job! What is the other error you get after resizing? I think 4,3,384,384 means batch size 4, 3 channels etc. Shouldn't you resize your input to 384x384 rather than...

@AIMads I'll check it out when I could, but that sounds as the neural model has fixed input size (architecture) of 96x96, so I guess your desired solution wouldn't fit...

I haven't trained such particular model, but I think you don't have to change the resolution, especially if your target will be 224x224 (i.e. not higher than the lower resolution...

I found a solution: I just manually set the paprameters of the device and skipped the check... :D ```python C:\DFL\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\core\leras\device.py ... skip_physical_devices = True ... @staticmethod def _get_tf_devices_proc(q : multiprocessing.Queue):...