tf.contrib.rnn.LSTMBlockCell

class tf.contrib.rnn.LSTMBlockCell

Basic LSTM recurrent network cell.

The implementation is based on: http://arxiv.org/abs/1409.2329.

We add forget_bias (default: 1) to the biases of the forget gate in order to reduce the scale of forgetting in the beginning of the training.

Unlike BasicLSTMCell, this is a monolithic op and should be much faster. The weight and bias matrixes should be compatible as long as the variabel scope matches.

Links:

https://www.tensorflow.org/versions/master/api_docs/python/contrib.rnn.html#LSTMBlockCell

doc_TensorFlow

2016-10-14 13:07:25

Comments

Popular Articles

tf.contrib.rnn.LSTMBlockCell.__call__() tf.contrib.rnn.LSTMBlockCell.__call__(x, states_prev, scope=None) Long short-term memory cell (LSTM).

tf.contrib.rnn.LSTMBlockCell.__init__() tf.contrib.rnn.LSTMBlockCell.__init__(num_units, forget_bias=1.0, use_peephole=False) Initialize the basic LSTM cell. Args: num_units: int, The num

tf.contrib.rnn.LSTMBlockCell.zero_state() tf.contrib.rnn.LSTMBlockCell.zero_state(batch_size, dtype) Return zero-filled state tensor(s). Args: batch_size: int, float, or unit Tensor represe

tf.contrib.rnn.LSTMBlockCell.state_size tf.contrib.rnn.LSTMBlockCell.state_size

tf.contrib.rnn.LSTMBlockCell.output_size tf.contrib.rnn.LSTMBlockCell.output_size