Utils

This module contains utility functions for neural knowledge graph embedding models.

This module contains utility functions for Knowledge Graph Embedding models.

Saving/Restoring Models

Models can be saved and restored from disk. This is useful to avoid re-training a model. On the contrary of what happens for save_weights() and save_weights(), the functions below allow to restart the model training from where it was interrupted when the model was first saved.

save_model(model[, model_name_path, protocol])	Save a trained model to disk.
restore_model([model_name_path])	Restore a trained model from disk.

Visualization

Functions to visualize embeddings.

create_tensorboard_visualizations(model, loc)

Export embeddings to Tensorboard.

Others

Function various functions to be used at need.

dataframe_to_triples(X, schema)	Convert DataFrame into triple format.
preprocess_focusE_weights(data, weights[, ...])	Preprocessing of focusE weights.