Размер батча — количество примеров, обрабатываемых вместе за один шаг обучения или инференса. Малые размеры батча могут обеспечивать более частые обновления, но более шумные градиенты, тогда как большие батчи могут улучшать использование оборудования, но требовать больше памяти. Мини-батчевое обучение использует промежуточные размеры батча и распространено в современном машинном обучении.
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.