Specify the data. Data names will be data_0, data_1, ..., etc.
Same as data, but is not fed to the model during testing. Label names will be label_0, label_1, ..., etc.
Batch Size
Whether to shuffle the data
"pad", "discard" or "roll_over". How to handle the last batch This iterator will pad, discard or roll over the last batch if the size of data does not match batch_size. Roll over is intended for training and can cause problems if used for prediction.
Specify the data as well as the name. NDArrayIter supports single or multiple data and label.
Same as data, but is not fed to the model during testing.
Batch Size
Whether to shuffle the data
"pad", "discard" or "roll_over". How to handle the last batch This iterator will pad, discard or roll over the last batch if the size of data does not match batch_size. Roll over is intended for training and can cause problems if used for prediction.
(Changed in version 2.8.0) collect
has changed. The previous behavior can be reproduced with toSeq
.
get data of current batch
the index of current batch
the index of current batch
Get label of current batch
Get label of current batch
the label of current batch
get the number of padding examples in current batch
get the number of padding examples in current batch
number of padding examples in current batch
Igore roll over data and set to start
get next data batch from iterator
get next data batch from iterator
reset the iterator
reset the iterator
(Since version 1.3.0) Please use provideDataDesc instead
(Since version 1.3.0) Please use provideLabelDesc instead
NDArrayIter object in mxnet. Taking NDArray to get dataiter.