lsch
lsch
What about animated AVIF? (e.g. something like GIFs)
@SthPhoenix gotcha, thanks for the info :)
@zhengzangw Can you elaborate how many H100 GPUs you currently require for training?
> 12x8 What is rougly the duration for it? (e.g. for hitting convergence)
WIP https://github.com/lschaupp/GFPGAN-onnxruntime-demo allows conversion to static batching. Currently exploring dynamic batching.
Yes I made it work. I am getting 70 ms runtime on 3060 RTX for the 512 upscale model. (GFPGAN 1.4) using TensorRT. (without pre and post processing) However the...
@nelsontseng0704 the fork has a different purpose. It is intended to construct a python wrapper around the C++ code for inference. For GFPGAN I made it work with the official...
You would need to debug the error within the C++ code. Cuda 700 is a standard error which does not tell much.