operator 'aten::std_mean.correction' is not currently supported on the DML backend

[tinnet]

I've encountered another operator that has to fallback on the CPU in DML, couldn't find it in the roadmap wiki.

...\Fooocus_win64_2-1-791\Fooocus\modules\anisotropic.py:132: UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the DML backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at D:\a_work\1\s\pytorch-directml-plugin\torch_directml\csrc\dml\dml_cpu_fallback.cpp:17.)
s, m = torch.std_mean(g, dim=(1, 2, 3), keepdim=True)

For context this is using Fooocus on a Radeon 7800xt

[rickfeldschau]

Same issue here, and requesting implementation of aten::std_mean.correction because this should speed up model loading as currently implemented in Fooocus.

However, this, in part, is due to relatively recent changes to speed things up in Fooocus' code. For more information, I've opened up an issue on the Fooocus repo.

[Thelionsfan]

Anyone figure out how to fix this?

[moharnab123saikia]

Same issue I found today.

[Thelionsfan]

Still no fix?

[Samkist]

also have this issue.

[f0n51]

Same issue here

[patientx]

rx 6600 , same problem. If we cancel the gen, it doesn't appear on the other ones. I don't know it is still in effect though.

[virenchocha]

Same issue here. AMD VEGA TM8 integrated graphics. Should we do overclocking with AMD GPUs?