Onur-Andros Özbek
Onur-Andros Özbek
> you should be able to use the torchvision library to save every tensor in the images dict How can I do that? Can you show me a demo?
No. This is a dead repo and the author has no interest in addressing these problems.
@Elsaam2y I select `rct` for color transfer. This is data_src: https://drive.google.com/drive/folders/1NUsGGAmE0vSZdiDy23c3DUhALqpuGE9P?usp=sharing This is data_dst: https://drive.google.com/file/d/1HMm5-wDgr7qvtj0Pqvdd7_5lTxYyfWJq/view?usp=sharing
> > I can't find a specific method to generate mat files on your home page. I am a novice. I hope you can give me as detailed steps as...
> Also, the said python file does NOT generate a .mat file.
I have 40GB of CUDA memory. Look at my nvidia-smi output. This is in a Determined.ai ntebook instance.
@8bignic8 How can I find the source of the split? This is my nvidia-smi ``` Tue Nov 15 09:36:39 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 510.60.02 Driver Version: 510.60.02 CUDA Version: 11.6...
@8bignic8 My Graphics card has 82gb of RAM
@zhanglonghao1992 Faceswapping algorithm does not work for beards, especially prominent ones.
Say that selfie_1 (with beard) is looking straight and selfie_2 is looking to the left. I don't want to do a face swap. I want to move selfie_1's head to...