TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.contrib.rnn.best_effort_input_batch_size

View source on GitHub

Get static input batch size if available, with fallback to the dynamic one.

tf.contrib.rnn.best_effort_input_batch_size(flat_input)

Args:

  • flat_input: An iterable of time major input Tensors of shape [max_time, batch_size, ...]. All inputs should have compatible batch sizes.

Returns:

The batch size in Python integer if available, or a scalar Tensor otherwise.

Raises:

  • ValueError: if there is any input with an invalid shape.