Vladimir

Some tips on solving that can be found [here](https://gprivate.com/60jqj).

Y'all need to look into the HLS installation documentation. Make sure you're using a supported version of Linux and have installed the required libraries (like gcc multilib). Vivado installation won't...

This looks good to me. The main concern I had was if this breaks the qkeras optimizers, but it seems like it doesn't. The key enhancement (getting the output nodes...

Since Benjamin is back at university now, I resolved the two issues, can you merge now @thesps ?

Since [94dbe80](https://github.com/fastmachinelearning/hls4ml/pull/629/commits/94dbe80fc3e6d821edad5ad50e32396ef5589cd9) there is support for resource strategy in Dense/Conv layers. The one corner case (when `rf > n_in & rf % n_in != 0`) still uses `urem` cores, but...

If the process died -> you ran out of memory (physical + swap) If the process is seemingly stuck/frozen or takes unreasonably long time -> you ran out of physical...

Could it be an issue of random seed? Maybe you can reproduce if you pass extra parameters, like [here](https://github.com/fastmachinelearning/hls4ml/blob/main/test/pytest/ci-template.yml#L13). That `--randomly-seed=42` parameter may be enough.

`use_legacy_format` comes from keras serialization functions. You need the latest TF installation for QKeras main. That's a bummer, we need them to make a release and fix on that. 0.9.0...

Looks like a real error, probably something was generated with a syntax error.

Yes, it is still under consideration for merging, hopefully we'll decide on Friday whether to include it in this release cycle (as an experimental feature) or postpone it to the...