Open carljohnsen opened 2 years ago
The current binary format reader reads the file sequentially, but should be done in parallel to speed up I/O.
It should, in the same go, be updated to handle strides in order to only read slices of the dataset.
The current binary format reader reads the file sequentially, but should be done in parallel to speed up I/O.
It should, in the same go, be updated to handle strides in order to only read slices of the dataset.