Expand description
A collection of data utility classes such as one_hot_encode() and SubsetIterator.
Structs
A utility class to simplify sampling a fixed number of indices for
data from a dataset.
Functions
Generates a tensor with ordered data from 0 to
N.One hot encodes an array of class labels into a Tensor2D of probability
vectors. This can be used in tandem with crate::losses::cross_entropy_with_logits_loss().