Chris-fullerton

> It tells you that some operators will be assigned to be run on CPU, so you should specify the CPU provider in the init option. Thanks for your answer,...

I am not pretty sure but seems that it's impossible to install onnxruntime-gpu now. I temporary solve this problem by loading the model of detection ONLY, instead of loading ALL...

@nttstar Have I miss understanded your answer? Already tried but `onnxruntime-gpu` cannot be installed on Mac M1 Ventura 13.0. > I am not pretty sure but seems that it's impossible...

Any news about this issue? @nttstar

> with mac m1/m2 u should use `onnxruntime-silicon` instead @phineas-pta Half right half wrong for me. --- [onnxruntime-silicon](https://github.com/cansik/onnxruntime-silicon) is made for `CoreML` > The official [ONNX Runtime](https://pypi.org/project/onnxruntime/1.13.1/#files) now contains arm64...

> u have to find a windows pc with roughly same config as your mac to make proper comparison Sorry about forgeting mention this before, I have already test with...

> that's literally my 1st paragraph > again, for comparison, windows pc must have same specs as mac in terms of SSD + RAM speed, also whether windows pc using...

> (just like other person commented on your other issue) @phineas-pta btw, isn't https://github.com/deepinsight/insightface/issues/2238#issuecomment-1481081198 prove that `insightface` doesn't support `CoreML`? (that's me actually, it's mine personal account, and this one...

> maybe because newer `onnxruntime` Sounds like a good research direction, thanks for your helping 👍

> This line seems to be the problem. Query selector returns null. > > https://github.com/domeccleston/sharegpt/blob/3ceca3aba9b62ae49546ebb0dd516ac7addf2926/extension/index.js#L46 Seems like it's just a line of unused code https://github.com/domeccleston/sharegpt/issues/114 ?