search

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.84k stars 2.94k forks source link

More supported ai.onnx operators for WebGL backend #11872

Open FabioRomagnolo opened 2 years ago

FabioRomagnolo commented 2 years ago

Hi! I'm currently working on a complex network, which took up 1s of inference using WASM backend. So I'm trying to convert the model to run inference using WEBGL backend in shorter time, but the simple conversion of params to int32 is not enough.

Is there any hope that the following operators will be supported by ONNX Runtime Web's WebGL backend?

The list of current available operators is here and in fact any of these operators is there. ONNX Runtime Web is very powerful and in my opinion so much better than TensorflowJS, but these unsopported operators are so annoying.

Any suggestion on how to implement this even if alone is welcome.

erikvdplas commented 1 year ago

Any update on this? (@FabioRomagnolo). To me, especially Constant/ConstantOfShape seems like a must-have, but also seemingly low-hanging fruit. I don't know much about the implementation of WebGL operators, but I'd be willing to contribute if someone can help me get started.