A sampler used to samples the batches where each instances is sampled twice
Arguments
- vaeac_dataset_object
A
vaeac_dataset()
object containing the data.- shuffle
Boolean. If
TRUE
, then the data is shuffled. IfFALSE
, then the data is returned in chronological order.
Details
A sampler object that allows for paired sampling by always including each observation from the
vaeac_dataset()
twice. A torch::sampler()
object can be used with torch::dataloader()
when creating
batches from a torch dataset torch::dataset()
. See https://rdrr.io/cran/torch/src/R/utils-data-sampler.R for
more information. This function does not use batch iterators, which might increase the speed.