This will download the model to the specified directory, as a Tensorflow Saved Model.
All models are trained and exported with Tensorflow 2.1.0.
What about the pre-processing?
All the pre-processing that you defined in the
preprocessing key is natively embedded into the model itself (with the exception of sequential
transformations - see below). This means that the
SavedModel itself can handle completely raw data by itself.
For now, sequential preprocessing like
forward_filling and anything defined in the
timeseries key is NOT embedded into the model. To
serve these models in production, please ensure that the data is in preprocessed with the same steps outlined in the pipeline.