Ben Arnao

Yea the output is the same regardless of batch size, so probably what @mhattingpete said

Hi, thanks for the reply but I think you may have misunderstood my question. Sorry if I was not clear. In the documentation for SGDW it is recommend that you...

@seanpmorgan Maybe something like ReduceLRonPlateauWithWeightDecay would be most descriptive, that is getting rather wordy though. However all scenarios in which we are reducing lr we should really be reducing wd...

Seems like an issue with TF not necessarily KT. Can you grab the params you use to create the model that crashes it and see if you can compile the...

Looks like at some point eager execution is getting turned off. Not sure why though...

For those still have the same issue here's how i solved it... ``` double validatePrice(double price) { if (price < minTradePrice) return 0; price -= (price - minTradePrice) % tickSize;...

`If you’re referring to using Categorical on the string names of optimizers, then “adamax” and “nadam” do work; however, I think I may have misunderstood.` adamax and nadam are callable...

I posted about this in another repo https://github.com/keras-team/keras-tuner/issues/287 I think there is an issue with simply rounding to discrete values due to the nature of BO. Since categorical parameters are...

@leifvan Hmm, i see. Are the helper variables separate dimensions when it comes to fitting the GPR? They would need to be in order to avoid the ordering bias i...

> > @leifvan Hmm, i see. Are the helper variables separate dimensions when it comes to fitting the GPR? They would need to be in order to avoid the ordering...