tf.compat.v1.nn.rnn_cell.LSTMStateTuple
Stay organized with collections
Save and categorize content based on your preferences.
Tuple used by LSTM Cells for state_size, zero_state, and output state.
tf.compat.v1.nn.rnn_cell.LSTMStateTuple(
c, h
)
Stores two elements: (c, h), in that order. Where c is the hidden state
and h is the output.
Only used when state_is_tuple=True.
Attributes |
|---|
c
|
A namedtuple alias for field number 0
|
h
|
A namedtuple alias for field number 1
|
dtype
|
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2022-09-07 UTC.
[null,null,["Last updated 2022-09-07 UTC."],[],[],null,["# tf.compat.v1.nn.rnn_cell.LSTMStateTuple\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.9.0/keras/layers/rnn/legacy_cells.py#L595-L613) |\n\nTuple used by LSTM Cells for `state_size`, `zero_state`, and output state. \n\n tf.compat.v1.nn.rnn_cell.LSTMStateTuple(\n c, h\n )\n\nStores two elements: `(c, h)`, in that order. Where `c` is the hidden state\nand `h` is the output.\n\nOnly used when `state_is_tuple=True`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|---------|-----------------------------------------|\n| `c` | A `namedtuple` alias for field number 0 |\n| `h` | A `namedtuple` alias for field number 1 |\n| `dtype` | \u003cbr /\u003e \u003cbr /\u003e |\n\n\u003cbr /\u003e"]]
View source on GitHub