Ping Yu

@ZackAkil tf.stack op is a relative simple op, the error you have observed seems to be very weird. We have tested on both linux and macbook (intel and m1) we...

@gyagp Thank you for the detail explanation, we would hope to unify the API between WebGL and WebGPU without major performance discrepancy, looking forward to the new timeout mechanism. thanks.

@FabioRomagnolo thanks for the feature request, base on the definition of ScatterNdUpdate the input reference tensor should be a variable tensor. which is not supported in our GraphModel, can you...

@jenperson @mattsoulanille Given the model contains two outputs, my guess it might not be a pure automl image classification model, or there are changes to the structure of the model.

The signature of this model looks like object detection model, instead of image classification model. Can you share how you have created this model?

@vladmandic Please check out the [code example](https://github.com/tensorflow/tfjs-examples/tree/master/gpu-pipeline) on how to use dataToGPU with WebGL.

@vladmandic your snippet capture the essense of the API, thanks. @lina128 Please take a look at the comments, maybe we should add this example to the API doc.

the URL of the benchmark page should reflect the settings dynamically, basically when users copy the url and sharing the settings are shared directly. the param/value pairs on the url...

We are happy to promote your work, you can submit a PR to add your link to our gallery page. Also feel free to reach out to our Developer relationship...

hi @FabioRomagnolo It could very possible that during the conversion of PyTorch => Onnx => TF => TFJS something might have lost in translation. Can you help to create a...