Pads all sequences to the same length. The length is defined by the longest sequence. Returns padded sequences.

resnet > res5c, pool5 c3d > fc6, conv5b concat > fc, conv

Gradient for BlockLSTM.

r"""Gradient for GRUBlockCell. Args: op: Op for which the gradient is defined. *grad: Gradients of the optimization function wrt output

Gradient for LSTMBlockCell.

Run this multi-layer cell on inputs, starting from state.

Run the cell with the declared dropouts.

Run the cell and add its inputs to its outputs. Args: inputs: cell inputs. state: cell state. scope: optional cell scope.

Run this fused RNN on inputs, starting from the given state. Args: inputs: `3-D` tensor with shape `[time_len x batch_size x input_size]`

Long short-term memory cell (LSTM).

Run this LSTM on inputs, starting from the given state. Args: inputs: `3-D` tensor with shape `[time_len, batch_size, input_size]`

GRU cell.

GRU cell.

Create a RNN cell composed sequentially of a number of RNNCells. Args: cells: list of RNNCells that will be composed in this order. s

Create a cell with added input and/or output dropout. Dropout is never used on the state. Args: cell: an RNNCell, a projection to outp

Create a cell with input projection. Args: cell: an RNNCell, a projection of inputs is added before it. num_proj: Python integer. Th

Create a cell with output projection. Args: cell: an RNNCell, a projection to output_size is added to it. output_size: integer, the s

Initializes the basic LSTM cell. Args: num_units: int, The number of units in the LSTM cell. forget_bias: float, The bias added to fo

Initialize the parameters for an LSTM cell. Args: num_units: int, The number of units in the LSTM cell use_peepholes: bool, set True

Initialize the parameters for an LSTM cell. Args: num_units: int, The number of units in the LSTM cell use_peepholes: bool, set True

Initialize the parameters for an LSTM cell. Args: num_units: int, The number of units in the LSTM cell use_peepholes: (optional) bool

Initialize the parameters for an LSTM cell. Args: num_units: int, The number of units in the LSTM cell use_peepholes: (optional) bool

Create a cell with attention. Args: cell: an RNNCell, an attention is added to it. attn_length: integer, the size of an attention win

Constructs a `HighwayWrapper` for `cell`. Args: cell: An instance of `RNNCell`. couple_carry_transform_gates: boolean, should the Car

Initializes the basic LSTM cell. Args: num_units: int, The number of units in the LSTM cell. forget_bias: float, The bias added to fo

Initializes the basic LSTM cell. Args: num_units: int, The number of units in the LSTM cell. forget_bias: float, The bias added to fo

Initialize the parameters for an UGRNN cell. Args: num_units: int, The number of units in the UGRNN cell initializer: (optional) The

Initialize the parameters for an +RNN cell. Args: num_units: int, The number of units in the +RNN cell num_in_proj: (optional) int, T

Create CompiledWrapper cell. Args: cell: Instance of `RNNCell`. compile_stateful: Whether to compile stateful ops like initializers

Initialize the Phased LSTM cell. Args: num_units: int, The number of units in the Phased LSTM cell. use_peepholes: bool, set True to

Construct ConvLSTMCell. Args: conv_ndims: Convolution dimensionality (1, 2 or 3). input_shape: Shape of the input as int tuple, exclud

Construct Conv1DLSTM. See `ConvLSTMCell` for more details.

Construct Conv2DLSTM. See `ConvLSTMCell` for more details.

Construct Conv3DLSTM. See `ConvLSTMCell` for more details.

Initialize the parameters of G-LSTM cell. Args: num_units: int, The number of units in the G-LSTM cell initializer: (optional) The in

Initialize the adaptor. Args: cell: an instance of a subclass of a `rnn_cell.RNNCell`. use_dynamic_rnn: whether to use dynamic (or st

Initialize the basic LSTM cell. Args: num_units: int, The number of units in the LSTM cell. forget_bias: float, The bias added to for

Initialize the LSTM cell. Args: num_units: int, The number of units in the LSTM cell. forget_bias: float, The bias added to forget ga

Initialize the Block GRU cell. Args: num_units: int, The number of units in the GRU cell. cell_size: int, The old (deprecated) name f

r"""TODO(williamchan): add doc. Args: seq_len_max: A `Tensor` of type `int64`. x: A list of at least 1 `Tensor` objects of the same type in

Run this LSTM on inputs, starting from the given state. Args: inputs: `3-D` tensor with shape `[time_len, batch_size, input_size]` in