tf.contrib.rnn.GRUCell

class tf.contrib.rnn.GRUCell

class tf.contrib.rnn.core_rnn_cell.GRUCell

See the guide: RNN and Cells (contrib) > Core RNN Cells for use with TensorFlow's core RNN methods

Gated Recurrent Unit cell (cf. http://arxiv.org/abs/1406.1078).

Properties

output_size

state_size

Methods

__init__(num_units, input_size=None, activation=tf.tanh)

zero_state(batch_size, dtype)

Return zero-filled state tensor(s).

Args:

• batch_size: int, float, or unit Tensor representing the batch size.
• dtype: the data type to use for the state.

Returns:

If state_size is an int or TensorShape, then the return value is a N-D tensor of shape [batch_size x state_size] filled with zeros.

If state_size is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of 2-D tensors with the shapes [batch_size x s] for each s in state_size.

Defined in tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py.