create_tensorboard_visualizations¶
-
ampligraph.utils.
create_tensorboard_visualizations
(model, loc, labels=None)¶ Create Tensorboard visualization files.
Note: this will create all the files required by Tensorboard to visualize embeddings, but you must run Tensorboard yourself.
Examples
>>> from ampligraph.utils import create_tensorboard_visualizations, restore_model >>> import numpy as np >>> example_name = 'helloworld.pkl' >>> restored_model = restore_model(model_name_path = example_name) >>> output_path = 'model_tensorboard/' >>> create_tensorboard_visualizations(restored_model, output_path)
Parameters: - model (EmbeddingModel) – A trained neural knowledge graph embedding model, the model must be an instance of TransE, DistMult, ComplEx, or HolE.
- loc (string) – Directory where the files are written.
- labels (pd.DataFrame) – Label(s) for each embedding point in the Tensorboard visualization. Default behaviour is to use the embeddings labels included in the model.