Tolstoi Data Set

class deepobs.pytorch.datasets.tolstoi.tolstoi(batch_size, seq_length=50, train_eval_size=653237)[source]

DeepOBS data set class for character prediction on War and Peace by Leo Tolstoi.

Parameters:
  • batch_size (int) -- The mini-batch size to use. Note that, if batch_size is not a divider of the dataset size the remainder is dropped in each epoch (after shuffling).
  • seq_length (int) -- Sequence length to be modeled in each step. Defaults to 50.
  • train_eval_size (int) -- Size of the train eval dataset. Defaults to 653 237, the size of the test set.