FusedRNNCell - LostTech.TensorFlow Documentation

Type FusedRNNCell

Namespace tensorflow.contrib.rnn

Run this fused RNN on inputs, starting from the given state.

IGraphNodeBase inputs: `3-D` tensor with shape `[time_len x batch_size x input_size]` or a list of `time_len` tensors of shape `[batch_size x input_size]`.
object initial_state: either a tensor with shape `[batch_size x state_size]` or a tuple with shapes `[batch_size x s] for s in state_size`, if the cell takes tuples. If this is not provided, the cell is expected to create a zero initial state of type `dtype`.
DType dtype: The data type for the initial state and expected output. Required if `initial_state` is not provided or RNN state has a heterogeneous dtype.
object sequence_length: Specifies the length of each sequence in inputs. An `int32` or `int64` vector (tensor) size `[batch_size]`, values in `[0, time_len)`. Defaults to `time_len` for each element.
string scope: `VariableScope` or `string` for the created subgraph; defaults to class name.

ValueTuple<object, object>: A pair containing:
- Output: A `3-D` tensor of shape `[time_len x batch_size x output_size]` or a list of `time_len` tensors of shape `[batch_size x output_size]`, to match the type of the `inputs`. - Final state: Either a single `2-D` tensor, or a tuple of tensors matching the arity and shapes of `initial_state`.

Run this fused RNN on inputs, starting from the given state.

object inputs: `3-D` tensor with shape `[time_len x batch_size x input_size]` or a list of `time_len` tensors of shape `[batch_size x input_size]`.
object initial_state: either a tensor with shape `[batch_size x state_size]` or a tuple with shapes `[batch_size x s] for s in state_size`, if the cell takes tuples. If this is not provided, the cell is expected to create a zero initial state of type `dtype`.
object dtype: The data type for the initial state and expected output. Required if `initial_state` is not provided or RNN state has a heterogeneous dtype.
object sequence_length: Specifies the length of each sequence in inputs. An `int32` or `int64` vector (tensor) size `[batch_size]`, values in `[0, time_len)`. Defaults to `time_len` for each element.
object scope: `VariableScope` or `string` for the created subgraph; defaults to class name.

object: A pair containing:
- Output: A `3-D` tensor of shape `[time_len x batch_size x output_size]` or a list of `time_len` tensors of shape `[batch_size x output_size]`, to match the type of the `inputs`. - Final state: Either a single `2-D` tensor, or a tuple of tensors matching the arity and shapes of `initial_state`.