Create a dataloaders from a given `dblock`
CollabDataLoaders_from_dblock(
dblock,
source,
path = ".",
bs = 64,
val_bs = NULL,
shuffle_train = TRUE,
device = NULL
)
dblock
source
The folder where to work
The batch size
The batch size for the validation DataLoader (defaults to bs)
If we shuffle the training DataLoader or not
device
None