Using train, val data

[orenpapers]

Hi , I read your tutorials and I don't understand the relation between x, y, x_train, y_train, x_val and y_val in your framework. For example, here: https://nbviewer.jupyter.org/github/autonomio/talos/blob/master/examples/A%20Very%20Short%20Introduction%20to%20Hyperparameter%20Optimization%20of%20Keras%20Models%20with%20Talos.ipynb The function: def diabetes(x_train, y_train, x_val, y_val, params): get the arguments : x_train, y_train, x_val, y_val But uses x,y in the .fit method within it. Moreover, in the line t = talos.Scan(x=x, y=y, params=p, model=diabetes, experiment_name='diabetes') What are x,y? Are they x_train, y_train?

[mikkokotila]

You should not mix two different concepts. One concept is the input mode def diabetes(...) which is an input to Scan(). x and y in Scan() are automatically handled to become x_train, y_train and so on in the input model.

Closing here. Feel free to open new issue if anything.