When would you use one or the other,Īnd how do they work? How to save and load a model Let's take a look at each of these options. This is generally used when training the model. Saving the architecture / configuration only, typically as a JSON file.Saving everything into a single archive in the TensorFlow SavedModel format.Or to only selectively save some of them: The Keras API makes it possible to save all of these pieces to disk at once, A set of losses and metrics (defined by compiling the model or calling.
An optimizer (defined by compiling the model).
0 kommentar(er)
