Reputation: 117
Had an issue with Attribute errors calling:
tf.nn.rnn(cell, inputs_series, initial_state=rnn_tuple_state)
Received an Attribute error:
AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'rnn'
Changed this to:
tf.contrib.rnn(cell, inputs_series, initial_state=rnn_tuple_state)
However, now I receive the following error:
TypeError: 'module' object is not callable
against the following line:
states_series, current_state = tf.contrib.rnn(cell, inputs_series, initial_state=rnn_tuple_state)
the code looks as follows:
# Forward passes
cell = tf.contrib.rnn.LSTMCell(state_size, state_is_tuple=True)
cell = tf.contrib.rnn.MultiRNNCell([cell] * num_layers, state_is_tuple=True)
states_series, current_state = tf.contrib.rnn(cell, inputs_series, initial_state=rnn_tuple_state)
Full Error:
Traceback (most recent call last):
File "/Users/glennhealy/PycharmProjects/lstm2/lstm2.py", line 49, in <module>
states_series, current_state = tf.contrib.rnn(cell, inputs_series, initial_state=rnn_tuple_state)
TypeError: 'module' object is not callable
Any Ideas??
tf.nn.rnn doesn't work, but neither does tf.contrib.rnn
Cheers in advance
Updated with more information based on responses
Looking at this, I have tried all the options in the tensorflgw_RNN information and I'm getting this error for a lot of them:
TypeError: static_bidirectional_rnn() got an unexpected keyword argument 'initial_state'
so, now I'm lost.
Upvotes: 1
Views: 1448
Reputation: 3356
According to the document https://www.tensorflow.org/api_guides/python/contrib.rnn
TensorFlow provides a number of methods for constructing Recurrent Neural Networks.
tf.contrib.rnn.static_rnn
tf.contrib.rnn.static_state_saving_rnn
tf.contrib.rnn.static_bidirectional_rnn
tf.contrib.rnn.stack_bidirectional_dynamic_rnn
Try this
tf.contrib.rnn.static_rnn(cell, inputs_series, initial_state=rnn_tuple_state)
or
tf.nn.static_rnn(cell, inputs_series, initial_state=rnn_tuple_state)
Upvotes: 1