You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I tried to run the code (python main.py --dataset ptb), and it failed with this exception:
...
Creating vocab...
After first pass of data, max word length is: 21
Token count: train 929589, val 73760, test 82430
Loading vocab...
Word vocab size: 10001, Char vocab size: 51
Reshaping tensors...
data load done. Number of batches in train: 265, val: 21, test: 23
Word vocab size: 10001, Char vocab size: 51, Max word length (incl. padding): 21
Traceback (most recent call last):
File "main.py", line 66, in <module>
tf.app.run()
File "/home/ndavid/venvs/embedding/local/lib/python2.7/site-packages/tensorflow/python/platform/default/_app.py", line 11, in run
sys.exit(main(sys.argv))
File "main.py", line 57, in main
data_dir=FLAGS.data_dir)
File "/mnt/store/ndavid/LM/Others/lstm-char-cnn-tensorflow/models/LSTMTDNN.py", line 86, in __init__
self.prepare_model()
File "/mnt/store/ndavid/LM/Others/lstm-char-cnn-tensorflow/models/LSTMTDNN.py", line 144, in prepare_model
cnn_output = highway(cnn_output, cnn_output.get_shape()[1], self.highway_layers, 0)
File "/mnt/store/ndavid/LM/Others/lstm-char-cnn-tensorflow/models/ops.py", line 28, in highway
output = f(rnn_cell.linear(output, size, 0, scope='output_lin_%d' % idx))
TypeError: 'module' object is not callable
I am using tensorflow version 0.5 (I think that's the latest one, but I am not sure).
The text was updated successfully, but these errors were encountered:
The most recent Tensorflow is 0.6 and I think there is a problem in rnn_cell.linear. In Tensorflow 0.5, linear was in rnn.linear not rnn_cell.linear. You'd better update it or chagne the path.
I tried to run the code (
python main.py --dataset ptb
), and it failed with this exception:I am using tensorflow version 0.5 (I think that's the latest one, but I am not sure).
The text was updated successfully, but these errors were encountered: