Batch size is the number of examples processed together in a single training or inference step. Small batch sizes can provide frequent updates but noisier gradients, while larger batches can improve hardware utilization but may require more memory. Mini-batch training uses intermediate batch sizes and is common in modern machine learning.
The number of examples in a batch. For instance, if the batch size is 100, then the model processes 100 examples per iteration. The following are popular batch size strategies: - Stochastic Gradient Descent (SGD), in which the batch size is 1. - Full batch, in which the batch size is the number of examples in the entire training set. For instance, if the training set contains a million examples, then the batch size would be a million examples. Full batch is usually an inefficient strategy. - mini-batch in which the batch size is usually between 10 and 1000. Mini-batch is usually the most efficient strategy. See the following for more information: - Production ML systems: Static versus dynamic inference in Machine Learning Crash Course. - Deep Learning Tuning Playbook.
The number of examples in a batch. For example, the batch size of SGD is 1, while the batch size of a mini-batch is usually between 10 and 1000. Batch size is usually fixed during training and inference; however, TensorFlow does permit dynamic batch sizes.