pandav2 / clockwork-rnn Goto Github PK

Hi,
I'm new to tensorflow so I could be wrong, but when I run main.py, I got an error showing

Traceback (most recent call last):
File "C:/.../Clockwork-RNN-master/main.py", line 35, in
model = ClockworkRNN(config)
File "C:...\Clockwork-RNN-master\models\clockwork_rnn.py", line 47, in init
self.create_model()
File "C:...\Clockwork-RNN-master\models\clockwork_rnn.py", line 123, in create_model
state = tf.concat(0, [partial_state, tf.slice(state, [active_rows, 0], [-1, -1])], name = 'new_state')
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1043, in concat
dtype=dtypes.int32).get_shape(
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 676, in convert_to_tensor
as_ref=False)
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 741, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\constant_op.py", line 113, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\constant_op.py", line 102, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 374, in make_tensor_proto
_AssertCompatible(values, dtype)
File "C:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 302, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).name))
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

I debug the code and find that the shape of 'state' variable is (36,1) and the code tries to slice it with begin = [ active_rows (=36) , 0 ]. Maybe the value is active_rows is incorrect? Or maybe I use a different version of tensorflow (my tf version is 1.2.1)?
Please let me know if you can confirm this error and what is the correct version of this line. Thanks a lot!
Regards,