CODEWITHSUNDEEP
tensorflowscoperecurrent-neural-network
Conan
Conan

Reputation: 59

Tensorflow RNN variable_scope error

I'm trying to make multi-layer RNN without using MultiRNNCell, because I want to update each layer independently. So I didn't use tf.dynamic_rnn. 

with tf.variable_scope("cell"):
  with tf.variable_scope("cell_1", reuse=True):
    cell_1 = tf.contrib.rnn.BasicLSTMCell(n_hidden)
    states_1 = cell_1.zero_state(batch_size, tf.float32)

  with tf.variable_scope("cell_2", reuse=True):
    cell_2 = tf.contrib.rnn.BasicLSTMCell(n_hidden)
    states_2 = cell_2.zero_state(batch_size, tf.float32)

  with tf.variable_scope("cell_3", reuse=True):
    cell_3 = tf.contrib.rnn.BasicLSTMCell(n_hidden)
    states_3 = cell_3.zero_state(batch_size, tf.float32)

outputs_1=[]
outputs_2=[]
outputs_3=[]

with tf.variable_scope("architecture"):
  for i in range(n_step):
    output_1, states_1 = cell_1(X[:, i], states_1)
    output_2, states_2 = cell_2(output_1, states_2)
    output_3, states_3 = cell_3(output_2, states_3)
    outputs_3.append(output_3)

Then I got error like this.

ValueError: Variable architecture/basic_lstm_cell/kernel already exists, disallowed. Did you mean to set reuse=True in VarScope?

So it seems like impossible to declare multiple cell in tensorflow without MultiRNNCell. How can I solve this?

Upvotes: 1

Views: 229

Answers (1)

Conan
Conan

Reputation: 59

I solved the problem and share the answer.

cell = tf.contrib.rnn.BasicLSTMCell(n_hidden)
cell2 = tf.contrib.rnn.BasicLSTMCell(n_hidden)
cell3 = tf.contrib.rnn.BasicLSTMCell(n_hidden)

states = cell.zero_state(batch_size, tf.float32)
states2 = cell2.zero_state(batch_size, tf.float32)
states3 = cell3.zero_state(batch_size, tf.float32)

outputs=[]
for i in range(n_step):
  with tf.variable_scope("cell1"):
    output, states = cell(X[:, i], states)
  with tf.variable_scope("cell2"):
    output2, states2 = cell2(output, states2)
  with tf.variable_scope("cell3"):
    output3, states3 = cell3(output2, states3)

  outputs.append(output3)

Upvotes: 1

Related Questions