syft.frameworks.keras.model¶
Submodules¶
Package Contents¶
-
syft.frameworks.keras.model.serve(model, num_requests=5)¶ Serve the specified number of predictions using the shared model, blocking until completed.
Secret share the model between workers.
This is done by rebuilding the model as a TF Encrypted model inside target_graph and pushing this graph to TFEWorkers running the cluster.
Note that this keeps a TensorFlow session alive that must later be shutdown using model.stop().
-
syft.frameworks.keras.model.stop(model)¶ Shutdown the TensorFlow session that was used to serve the shared model.