Sioni Summers

Hi, I hope you don't mind me weighing in @zhuangh . Could it be due to the `alpha` parameter and `scale`? @rdp23, you could try probing the `scale` attribute of...

I think we could now remove these `enable_if` constructions altogether, or at least simplify the logic a lot. The logic to decide which is the appropriate `cast` function is essentially...

Thanks for flagging this. @vloncar I think you encountered it at some point too, right? Or at least I remember you describing that warning too. In terms of correcting it......

Hi, is the problem really the synthesis, or getting good agreement between hls4ml and Keras so far? For a model trained with floating point weights and activations, one needs to...

From your example (thanks for providing something easy to run), I made some small tweaks: - After creating the hls4ml configuration on line 171, enable tracing of all layers: ```...

I like this, but I think we may still need some manual action involved just as a protection. I've seen examples where a specific comment like "run tests" by an...

The problem is related to the `gmp` library & an issue with Vivado HLS, see [here](http://svn.clifford.at/handicraft/2017/vivadobugs/vivadobug04.txt) for example.

Hi, I don't have the answer to your issue unfortunately, but others might. However, since you mention Pynq-ZU, would you be willing to help develop and test the support for...

I've pushed the prototype Pynq ZU support to the [pynq-zu branch](https://github.com/fastmachinelearning/hls4ml/tree/pynq-zu). You can install it directly like `pip install git+https://github.com/fastmachinelearning/hls4ml@pynq-zu`. In order to test it, you should be able to...

I like the idea, but I think the implementation could be handled differently. Am I right thinking that this "strategy argmax" effectively replaces the softmax function with a linear activation?...