tf.compat.v1.nn.rnn_cell.GRUCell

View source on GitHub

Gated Recurrent Unit cell (cf.

tf.compat.v1.nn.rnn_cell.GRUCell(
    num_units, activation=None, reuse=None, kernel_initializer=None,
    bias_initializer=None, name=None, dtype=None, **kwargs
)

http://arxiv.org/abs/1406.1078).

Note that this cell is not optimized for performance. Please use tf.contrib.cudnn_rnn.CudnnGRU for better performance on GPU, or tf.contrib.rnn.GRUBlockCellV2 for better performance on CPU.

Args:

Attributes:

Methods

get_initial_state

View source

get_initial_state(
    inputs=None, batch_size=None, dtype=None
)

zero_state

View source

zero_state(
    batch_size, dtype
)

Return zero-filled state tensor(s).

Args:

Returns:

If state_size is an int or TensorShape, then the return value is a N-D tensor of shape [batch_size, 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, s] for each s in state_size.