Vladimir Mandic

yes, i was wrong. but at least i managed to find it at the end :) seems its an actual bug in implementation of `tf.conv2d` actual function in FaceAPI is...

@mayankagarwal-cf just closing the loop... it seems that issue was `conv2d` implementation in old **TF1** binaries which were used by `tfjs-node` `tfjs-node` **3.5.0** finally ships with TF2 binaries and this...

it's exactly what it says 'image has not completed loading' - assigning `imgRef.src` is ok, but then execute actual detection inside event that triggers when image is loaded, something like...

`faceapi` has not been updated for a long time, so that's main reason why this port exists:

@jeffreytgilbert > Recent posts on TensorFlow's blog make me think maybe there is another model that could be loaded up and used for fast results and more detailed info. I've...

Agree, `WebGPU` use-case is in-browser, not catch-all. But regarding WebNN, etc. - I don't see how a committee driven backend designed for high-level usage can accomplish much other than increase...

I definitely don't see a scenario where TFJS loads a model and then passes it to WebNN for execution - why would devs maintain TFJS then? Just as a loader?...

example using canvas: example using tfjs native functions:

it works with m and g variations, but not with t (transformer). there is one trivial change needed: ```js const baseSize = strideSize * 13; ``` should be `* 10`...

@batrlatom here's a link, i'll keep it up for few days: