Mikko Kotila

`def create_model(X_input, y_input, params)` is wrong. You must declare it exactly like the docs explain for the input model. For example: `def iris_model(x_train, y_train, x_val, y_val, params):`

Let's have a look into this. Some of the higher priority items like full support for multi-input models, and distributed experiments have now been completed, so I think this could...

@krwiegold @alexcwsmith can you help and share one or two code complete examples in Google Colab where such a model is running without Talos. Also, had you any thoughts about...

I think best make it into a dictionary. The goal here is to be able to feed back to the experiment programmatically.

Very interesting. Can you share more about the underlying use-case?

Related with #158

`exclude` is so that you can drop columns (usually metrics) because doing a statistical correlation for example with three different metrics makes no sense. Just input the columns to drop...

Please post the entire trace.

Can you post the entire trace i.e. the entire message with the error.

Thanks for suggesting this. It is indeed a useful feature, but will require some thinking and testing in terms of implementing it. There are three parts to this: 1) storing...