Using the same model for different data sets

[howardnewyork]

It appears that when you write a Greta model, the data is "bound" to the model. Is it possible to write a model, compile it, and then feed the compiled model different data sets? This is useful if you are running the same model over 100s of datasets.

[goldingn]

That will be made possible soon, as we're also planning to enable inference methods that enable using a different minibatch of data at each iteration.

A limitation of that mechanism is that the datasets will have to have identical dimensions. If you want to fit the same model to datasets with different dimensions (e.g. different numbers of observations) the easiest thing would be to write a function to build (and possibly fit) a greta model to a given dataset, then loop over that function feeding the datasets.

[goldingn]

See this post on the forum for a hacked together implementation of batching. Feedback veery welcome!