Anpei Chen

No, this repo just an exercise, thanks.

I think it is because your project path contain some space characters: ` C:\Users\LINK\OneDrive - University of Waterloo\SYDE 671 project\released_v0.1\` I hope this is helpfully to you.

did the problem solve? if not, please check the image path, it seems "img_path" is incorrect, you may need to replace the "img_path" with your real path, e.g., "e:/something/xxx.png"

Hi, for the nose issue, please refer to [this](https://github.com/apchenstu/Facial_Details_Synthesis/issues/12#issuecomment-528824360). Thanks.

Yes, texture render is independent with other programs, you can simply run it via command line. Could you provide me more information? For example, your input command line, input files,...

sorry for replying late, did you resolve this issue?

one gpu should be fine, I didn't occur this issue before, could you post your pytorch, cuda version and GPU types?

> Thank you for responding so quickly! > My running environment: > torch==1.2.0 > CUDA==10.0 > GPU==GTX 1650Ti so weird and sorry I couldn't figure out the problem.

Hi, our method is to predict facial detail path-ly (256*256) from a given image, so there is some overlap between paths. we use a "count" variable to accumulate the overlap...

it looks likes the renderer attempts to load the obj file but it doesn't exist, so please check whether the folder exists the file "D:\PycharmProjects\init_facial_fidelity_capture\results\019615\result.obj",