shuffle - Shuffle data in minibatchqueue - MATLAB (original) (raw)

Main Content

Shuffle data in minibatchqueue

Since R2020b

Syntax

Description

shuffle([mbq](#mw%5F78b30cfd-7a9c-44d3-8fef-a45745547171%5Fsep%5Fmw%5F1052debc-abad-4547-9b2c-423b954fdb8a)) resets the data held inmbq and shuffles it into a random order. After shuffling, the next function returns different mini-batches. Use this syntax to reset and shuffle your data after each training epoch in a custom training loop.

Examples

collapse all

Differences Between `shuffle` and `reset`

The shuffle function resets and shuffles theminibatchqueue object so that you can obtain data from it in a random order. By contrast, the reset function resets theminibatchqueue object to the start of the underlying datastore.

Create a minibatchqueue object from a datastore.

ds = digitDatastore; mbq = minibatchqueue(ds,MiniBatchSize=256)

mbq = minibatchqueue with 1 output and properties:

Mini-batch creation: MiniBatchSize: 256 PartialMiniBatch: 'return' MiniBatchFcn: 'collate' PreprocessingEnvironment: 'serial'

Outputs: OutputCast: {'single'} OutputAsDlarray: 1 MiniBatchFormat: {''} OutputEnvironment: {'auto'}

Obtain the first mini-batch of data.

Iterate over the rest of the data in the minibatchqueue object. Usehasdata to check if data is still available.

while hasdata(mbq) next(mbq); end

Shuffle the minibatchqueue object and obtain the first mini-batch after the queue is shuffled.

shuffle(mbq); X2 = next(mbq);

Iterate over the remaining data again.

while hasdata(mbq) next(mbq); end

Reset the minibatchqueue object and obtain the first mini-batch after the queue is reset.

reset(mbq); X3 = next(mbq);

Check whether the mini-batches obtained after resetting or shuffling theminibatchqueue object are the same as the first mini-batch after the minibatchqueue object is created.

isequal(X1,X2) isequal(X1,X3)

The reset function returns the minibatchqueue object to the start of the underlying data, so that the next function returns mini-batches in the same order each time. By contrast, theshuffle function shuffles the underlying data and produces randomized mini-batches.

Version History