改编喀拉拉邦模型 [英] shuffle in the model.fit of keras

问题描述

在keras的model.fit中，有一个shuffle参数，

shuffle: Boolean (whether to shuffle the training data before each epoch) or str (for 'batch'). 'batch' is a special option for dealing with the limitations of HDF5 data; it shuffles in batch-sized chunks. Has no effect when steps_per_epoch is not  None.

假设训练集是一个包含50000个元素的列表，那么整个列表将在每个时期之前随机排列吗?如果批处理大小为250，那么仅属于每个批处理的元素会被置换?什么是正确的理解?

Assume the training set is a list with 50000 elements, so the whole list will be randomly permuted before each epoch? Of if the batch size is 250, only the elements belonging to each batch get permuted? What should be the correct understanding?

推荐答案

它将

It will shuffle your entire dataset (x, y and sample_weight together) first and then make batches according to the batch_size argument you passed to fit.

这篇关于改编喀拉拉邦模型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！