Glossary term
Glossary term
Foundations
The set of examples used in one training iteration. The batch size determines the number of examples in a batch.
See epoch for an explanation of how a batch relates to an epoch.
See Linear regression: Hyperparameters in Machine Learning Crash Course for more information.
Created for this library
A click-prediction team configures a batch size of 8,192 to make full use of its TPU memory during training.
A computer vision team processes images in batches of 64 on a single GPU because larger batches would exceed memory.
A finance NLP team uses small batches of 16 long documents because each example consumes several megabytes of memory.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License