LSTM doesn't work
dimeldo opened this issue · comments
Changing the cell type to LSTM throws an error (with default parameters and code):
ValueError: Shape must be rank 2 but is rank 3 for 'model/concat' (op: 'ConcatV2') with input shapes: [?,30], [?,4], [?,4], [2,?,600], [].
Thanks for the heads up. I pushed the fixed solution. Closing issue.
After using your fix I get this error:
Traceback (most recent call last):
File "kgcvae_swda.py", line 172, in <module>
main()
File "kgcvae_swda.py", line 72, in main
model = KgRnnCVAE(sess, config, api, log_dir=None if FLAGS.forward_only else log_dir, forward=False, scope=scope)
File "/Downloads/NeuralDialog-CVAE/models/cvae.py", line 243, in __init__
input_embedding = tf.reshape(input_embedding, [-1, max_dialog_len, sent_size])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 3938, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 528, in _apply_op_helper
(input_name, err))
ValueError: Tried to convert 'shape' to a tensor and failed. Error: Shapes must be equal rank, but are 0 and 1
From merging shape 1 with other shapes. for 'model/wordEmbedding/Reshape_2/packed' (op: 'Pack') with input shapes: [], [], [4].
How can I solve this error?