Comment Comment by aaron-santos What didn't work:Shipping pickled models to other teams.Deploying Sagemaker endpoints (too costly).Requiring editing of config files to deploy endpoints.What did work:Shipping http endpoints.Deriving api documentation from model docstrings.Deploying lambdas (less costly than Sagemaker endpoints).Writing a ~150 line python script to pickle the model, save a requirements.txt, some api metadata, and test input/output data.Continuous deployment (after model is saved no manual intervention if model response matches output data). parent aaron-santos 7 years ago
Shipping pickled models to other teams.
Deploying Sagemaker endpoints (too costly).
Requiring editing of config files to deploy endpoints.
What did work:
Shipping http endpoints.
Deriving api documentation from model docstrings.
Deploying lambdas (less costly than Sagemaker endpoints).
Writing a ~150 line python script to pickle the model, save a requirements.txt, some api metadata, and test input/output data.
Continuous deployment (after model is saved no manual intervention if model response matches output data).