Javier Duarte

@SteCla0 Can you provide a script or steps to reproduce the error? Do you also see it on the current master branch?

@vloncar oh yes definitely! I should have said this is just a placeholder / for discussion for now. I figured we'd rebase/merge it during a quiet time without other major...

I tried to use `clang-format` to format the HLS code with: ```yml --- # BasedOnStyle: Google ColumnLimit: 120 IndentWidth: 4 BreakBeforeBraces: Stroustrup ... ``` One issue is that pragmas are...

Hello @AnouarITI What version of hls4ml are you using? Could you send a script or gist to reproduce the error? Some recent updates may help this, e.g. https://github.com/fastmachinelearning/hls4ml/pull/443 https://github.com/fastmachinelearning/hls4ml/pull/472

Started with #528

This was introduced by my PR: #310, where I create a different intermediate model for each layer in order to provide the appropriate intermediate outputs. In particular, the issue is...

I agree with Sioni's comments and I would add there could be two different optimizer passes depending on the choice of strategy: - "argmax" -> replaces softmax with an argmax...

Started a branch to try to make some trivial changes to use the `vitis_hls` executable (https://github.com/fastmachinelearning/hls4ml/compare/master...jmduarte:vitis), but quickly found there are many issues to be fixed with pragmas that changed,...

Adding here the main pragma changes with Vitis HLS 2020.2 (thanks to @vloncar) and implications for hls4ml. Help and/or ideas are welcome for those interested in contributing to fixing some...

Hi @wilfredkisku, can you share your model. You may look into tracing / profiling functionality. You can make 1D plots of the expected output vs hls4ml output like so: https://github.com/hls4ml-finn-mlperftiny/CIFAR10/blob/main/hls4ml/convert.py#L222-L233...