Nicolò Ghielmetti

@zhuangh here a test --> https://gist.github.com/nicologhielmetti/84df61987476b031eb8fc6103f7e2915 @julesmuhizi and I compared the performance with a QDense + Batchnorm layer to see how much is the gap between the two. It actually...

Sure, @themachho here the branch for FIFO optimization --> https://github.com/nicologhielmetti/hls4ml/tree/fifo_depth_opt I would suggest you to use to this commit --> 888713b5d4dce0c4be0791794eca236892021819 **UPDATE** I cleaned the repo from the unrelated commit....

Hi, I would suggest to first of all check if `hls_model.predict(x)` (HLS model simulated on CPU) corresponds to `model.predict(x)`(Keras model); they should be at least close each other. If they...

I see some tests related to oneAPI fails; it's hard to me to understand why they fail, how should I proceed?

I'll take a look soon

Looks good to me. One small note, I think the test could be rewritten in a more `pytest` way, like this: ``` @pytest.mark.parametrize( "val, expected_width", [ (0, 1), (-1024, 2),...

Can it be extended in order to be applied to QONNX ingestion as well?

> I think the code in #979 infers the precision from the QONNX model, so that should be covered there. It does for weights/biases and in general for `Quant` nodes...

It looks very similar to this: https://adaptivesupport.amd.com/s/question/0D54U00006RvkkWSAR/how-can-i-add-properly-the-patch-y2k22patch12-to-vivado?language=en_US

I created a fix for this issue at QONNX level: ``` class FillEmptyRoI(Transformation): "Fill empty RoI input tensor of Resize node if is empty to avoid issues during shape inference"...