Tolstoi Data Set¶
-
class
deepobs.tensorflow.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.
-
batch
¶ A tuple
(x, y)
of tensors, yielding batches of tolstoi data (x
with shape(batch_size, seq_length)
) and (y
with shape(batch_size, seq_length)
which isx
shifted by one). Executing these tensors raises atf.errors.OutOfRangeError
after one epoch.
-
train_init_op
¶ A tensorflow operation initializing the dataset for the training phase.
-
train_eval_init_op
¶ A tensorflow operation initializing the testproblem for evaluating on training data.
-
test_init_op
¶ A tensorflow operation initializing the testproblem for evaluating on test data.
-
phase
¶ A string-value tf.Variable that is set to
train
,train_eval
ortest
, depending on the current phase. This can be used by testproblems to adapt their behavior to this phase.
- batch_size (int) -- The mini-batch size to use. Note that, if