Char RNN classification with batch size

[paulthemagno]

I'm replicating this example for a classification with a char-rnn.

for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss

I see that every epoch only 1 example is taken and random. I would like that each epoch all the dataset is taken with a specific batch size of examples. I can adjust the code to do this myself but I was wondering if some flags already exist.

Thank you