Python tensorflow.contrib.rnn.static_rnn() Examples
The following are 30
code examples of tensorflow.contrib.rnn.static_rnn().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorflow.contrib.rnn
, or try the search function
.
Example #1
Source File: word_rnn.py From tensorflow-nlp-examples with MIT License | 7 votes |
def RNN(x, weights, biases): # reshape to [1, n_input] x = tf.reshape(x, [-1, n_input]) # Generate a n_input-element sequence of inputs # (eg. [had] [a] [general] -> [20] [6] [33]) x = tf.split(x, n_input, 1) # 2-layer LSTM, each layer has n_hidden units. # Average Accuracy= 95.20% at 50k iter rnn_cell = rnn.MultiRNNCell([rnn.BasicLSTMCell(n_hidden), rnn.BasicLSTMCell(n_hidden)]) # 1-layer LSTM with n_hidden units but with lower accuracy. # Average Accuracy= 90.60% 50k iter # Uncomment line below to test but comment out the 2-layer rnn.MultiRNNCell above # rnn_cell = rnn.BasicLSTMCell(n_hidden) # generate prediction outputs, states = rnn.static_rnn(rnn_cell, x, dtype=tf.float32) # there are n_input outputs but # we only want the last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #2
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #3
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #4
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #5
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #6
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #7
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #8
Source File: tensorflow_LSTMs.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def LSTMs(x, weights, biases, timesteps , num_hidden): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #9
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #10
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #11
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #12
Source File: studyTF_LSTM_demo.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #13
Source File: studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #14
Source File: tensorflow_LSTMs.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def LSTMs(x, weights, biases, timesteps , num_hidden): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #15
Source File: tensorflow_LSTMs.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def LSTMs(x, weights, biases, timesteps , num_hidden): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #16
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #17
Source File: studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #18
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #19
Source File: studyTF_LSTM_demo.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #20
Source File: studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #21
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): timesteps = 28 # timesteps num_hidden = 128 # hidden layer num of features # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #22
Source File: use_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #23
Source File: train_studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #24
Source File: studyTF_LSTM_demo.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #25
Source File: studyTF_LSTM_demo_me.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #26
Source File: tensorflow_LSTMs.py From DeepLearning_Wavelet-LSTM with MIT License | 6 votes |
def LSTMs(x, weights, biases, timesteps , num_hidden): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, timesteps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #27
Source File: model.py From Relation-Network with MIT License | 6 votes |
def questionLSTM(self, q, q_real_len, reuse = False, scope= "questionLSTM"): """ Args q: zero padded qeustions, shape=[batch_size, q_max_len] q_real_len: original question length, shape = [batch_size, 1] Returns embedded_q: embedded questions, shape = [batch_size, q_hidden(32)] """ embedded_q_word = tf.nn.embedding_lookup(self.q_word_embed_matrix, q) q_input = tf.unstack(embedded_q_word, num = self.q_max_len, axis=1) lstm_cell = rnn.BasicLSTMCell(self.q_hidden, reuse = reuse) outputs, _ = rnn.static_rnn(lstm_cell, q_input, dtype = tf.float32, scope = scope) outputs = tf.stack(outputs) outputs = tf.transpose(outputs, [1,0,2]) index = tf.range(0, self.batch_size) * (self.q_max_len) + (q_real_len - 1) outputs = tf.gather(tf.reshape(outputs, [-1, self.s_hidden]), index) return outputs
Example #28
Source File: rnn_predicter.py From TensorFlow-Bitcoin-Robot with Apache License 2.0 | 6 votes |
def RNN(x, weights, biases): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, n_steps, n_input) # Required shape: 'n_steps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'n_steps' tensors of shape (batch_size, n_input) x = tf.unstack(x, n_steps, 1) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0) # Get lstm cell output outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out']
Example #29
Source File: ops.py From easy-tensorflow with MIT License | 6 votes |
def RNN(x, weights, biases, max_time, num_hidden): # Prepare data shape to match `rnn` function requirements # Current data input shape: (batch_size, timesteps, n_input) # Required shape: 'timesteps' tensors list of shape (batch_size, n_input) # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input) x = tf.unstack(x, max_time, 1) # Define a rnn cell with tensorflow # rnn_cell = rnn.BasicRNNCell(num_hidden) # Define a lstm cell with tensorflow lstm_cell = rnn.BasicLSTMCell(num_hidden) # Get lstm cell output # If no initial_state is provided, dtype must be specified # If no initial cell satte is provided, they will be initialized to zero # states_series, current_state = rnn.static_rnn(rnn_cell, x, dtype=tf.float32) outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32) # Linear activation, using rnn inner loop last output # return tf.matmul(current_state, weights) + biases return tf.matmul(outputs[-1], weights) + biases
Example #30
Source File: seq2seq_ops.py From keras-lambda with MIT License | 6 votes |
def rnn_seq2seq(encoder_inputs, decoder_inputs, encoder_cell, decoder_cell=None, dtype=dtypes.float32, scope=None): """RNN Sequence to Sequence model. Args: encoder_inputs: List of tensors, inputs for encoder. decoder_inputs: List of tensors, inputs for decoder. encoder_cell: RNN cell to use for encoder. decoder_cell: RNN cell to use for decoder, if None encoder_cell is used. dtype: Type to initialize encoder state with. scope: Scope to use, if None new will be produced. Returns: List of tensors for outputs and states for trianing and sampling sub-graphs. """ with vs.variable_scope(scope or "rnn_seq2seq"): _, last_enc_state = rnn.static_rnn( encoder_cell, encoder_inputs, dtype=dtype) return rnn_decoder(decoder_inputs, last_enc_state, decoder_cell or encoder_cell)