garage.tf.models.lstm module¶
LSTM in TensorFlow.
-
lstm
(name, lstm_cell, all_input_var, step_input_var, step_hidden_var, step_cell_var, output_nonlinearity_layer, hidden_state_init=<tensorflow.python.ops.init_ops.Zeros object>, hidden_state_init_trainable=False, cell_state_init=<tensorflow.python.ops.init_ops.Zeros object>, cell_state_init_trainable=False)[source]¶ Long Short-Term Memory (LSTM).
Parameters: - name (str) – Name of the variable scope.
- lstm_cell (tf.keras.layers.Layer) – LSTM cell used to generate outputs.
- all_input_var (tf.Tensor) – Place holder for entire time-seried inputs.
- step_input_var (tf.Tensor) – Place holder for step inputs.
- step_hidden_var (tf.Tensor) – Place holder for step hidden state.
- step_cell_var (tf.Tensor) – Place holder for cell state.
- output_nonlinearity_layer (callable) – Activation function for output dense layer. It should return a tf.Tensor. Set it to None to maintain a linear activation.
- hidden_state_init (callable) – Initializer function for the initial hidden state. The functino should return a tf.Tensor.
- hidden_state_init_trainable (bool) – Bool for whether the initial hidden state is trainable.
- cell_state_init (callable) – Initializer function for the initial cell state. The functino should return a tf.Tensor.
- cell_state_init_trainable (bool) – Bool for whether the initial cell state is trainable.
Returns: Entire time-seried outputs. output (tf.Tensor): Step output. hidden (tf.Tensor): Step hidden state. cell (tf.Tensor): Step cell state. hidden_init_var (tf.Tensor): Initial hidden state. cell_init_var (tf.Tensor): Initial cell state.
Return type: outputs (tf.Tensor)