Sioni Summers

This is the branch: https://github.com/thesps/hls4ml/tree/zcu104 I haven't made a PR yet since I don't have a ZCU104 to really validate it, but it's close enough to the ZCU102 that I...

Hi, have you tried using the profiling & tracing tools in hls4ml to pinpoint the first layer that has an issue? Perhaps you can include some of the plots which...

> The method breaks if granularity='name' is not used in hls4ml.utils.config_from_keras_model, though this feature is not just for these quantizers. You could move the new logic that sets the number...

Also can you push to a local branch (like `pr/569`) to trigger Gitlab CI for pytests?

I notice in the qkeras pytest we get: `E TypeError: __init__() got an unexpected keyword argument 'use_real_tanh'` It's because that option is in QKeras main branch but not in a...

So a few tests are still failing, including the existing `hard_sigmoid` tests in `test_activations`, some of which fail and at least one of which now creates a segmentation fault. The...

Thanks for the fix, I don't think we need a new test for this

Thanks for pointing this out. With which Tensorflow version do you see the small number of training samples?

Thanks for chasing it down! > I think it would be better to align the env file with what is used on jupiter hub. I agree, I will update the...

My apologies for that late response on this. We recently merged the `VivadoAccelerator` backend into the `hls4ml` master branch. That can help make a bitfile for Pynq-Z2 and ZCU104 boards...