Closed Justin62628 closed 1 year ago
I don't use pnnx. I use self written code and workarounds to export. The model itself won't change anyway, only the param file. Please test with my vapoursynth code again instead of nihui. It worked fine there iirc. I use different ncnn submodule, but I don't think that is it.
uh you're right. lmao after some debug I found that using Intel GPU is the reason for that overlayed output. NVIDIA GPU works like a charm.
Using the same script of inference implemented by nihui, the following models produce different outputs as followed: (
uhd_mode = False
andtta_mode = False
)rife-v4_ensembleTrue_fastFalse
orrife-v4_ensembleFalse_fastTrue
rife-4.5
andrife-4.6
, no matterensemble
is True or FalseThere might be a problem with the quantitization or conversion of the
ensemble
feature. Would it be convenient for you to share the scripts for model conversions(pytorch model to ncnn.params
&.bins
)? Nihui says she converted therife-v4
model usingpnnx
, which could make a difference I guess.