how does input_fn, predict_fn and output_fn work in aws sagemaker script mode?

Question

i am trying to understand how input_fn, predict_fn and outout_fn work? I am able to understand what they are, but I am not able to understand  how they are called (invoked), can anyone help me understand the same

Answer

Hi,

Take a look at this [implementation using scikit_learn](https://github.com/aws/sagemaker-scikit-learn-container/blob/master/src/sagemaker_sklearn_container/handler_service.py)

They are all implemented as part of the `HandlerService` object.

* `input_fn` for preprocessing when data comes in
* `predict_fn` for making a prediction
* `output_fn` for postprocessing

Generally, `input_fn` and `output_fn` have default implementations provided by SageMaker, but `predict_fn` does not.

how does input_fn, predict_fn and output_fn work in aws sagemaker script mode?

Conteúdo relevante