为什么预测需要Keras中的批量大小? [英] Why does prediction needs batch size in Keras?

问题描述

在Keras中，为了预测数据测试的类别，使用了predict_classes().

In Keras, to predict class of a datatest, the predict_classes() is used.

例如:

classes = model.predict_classes(X_test, batch_size=32)

我的问题是，我知道batch_size在训练中的用法，但是为什么需要batch_size进行预测?如何运作?

My question is, I know the usage of batch_size in training, but why does it need a batch_size for prediction? how does it work?

推荐答案

Keras可以同时预测多个值，就像输入100个元素的向量一样，Keras可以为每个元素计算一个预测，从而提供100个输出.此计算也可以按batch_size定义的批次进行.

Keras can predict multiple values at the same time, like if you input a vector of 100 elements, Keras can compute one prediction for each element, giving 100 outputs. This computation can also be done in batches, defined by the batch_size.

这是为了防止您无法同时将所有数据容纳在CPU/GPU RAM中并且需要批处理的情况.

This is just in case you cannot fit all the data in the CPU/GPU RAM at the same time and batch processing is needed.

这篇关于为什么预测需要Keras中的批量大小?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！