Henning Wilmer

I got the same Issues. Even with Models from the example folder.

Everytime I encountered the unrolling issues I just bumped up the `Reuse` to the maximum. Than it worked with normal FC networks.

I actually think you dont need to see the layers after optimization. You should concentrate on this part of the documentation. > As a starting point, a good configuration would...

My guess is, that the values before are the ones of the QKeras Model and the the after values are the ones of the hls_model, because hls4ml has to apply...

@rtspk thats what I though aswell, but my understanding was that QKeras quantized everything: the input, the weights and the Output, so the Output should have the same precision as...

This is my Config: ``` HLSConfig LayerName input_1_m Precision result: ap_fixed qact_1_m Precision result: ap_ufixed ReuseFactor: 2000000 Trace: True qact_2_m Precision result: ap_ufixed ReuseFactor: 2000000 Trace: True qdense_1_m Precision bias:...

Thank you. The only thing unclear atm is how do I set the `board` aswell? I saw there is a new AcceleratorConfig? And the Problem with double writing the Writing...

I found that if you set you `Backend: VivadoAccelerator` the BRAM usage will be a lot lower. For me it cut the usage in half. Why is that? These are...

@vloncar could you give me an example how to use the `BramFactor` in the config ?