Glossary term
Glossary term
Infrastructure and Serving
In TensorFlow, a value or set of values calculated at a particular step, usually used for tracking model metrics during training.
Created for this library
An ML team logs summary statistics like loss, accuracy, and gradient norms during training for monitoring and debugging.
A research team uses summary tables in TensorBoard to compare experiments side by side.
An ML platform team standardizes summary logging across training jobs so cross-experiment comparison is straightforward.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License