jostmey / rwa Goto Github PK

d₀ = 0 is missing in the equations.

Looks very interesting. I'd like to read the paper.

Hello, Earlier I had come across the recursive back propagation equations being used in RWA Now it seems to be unavailable.Could you please share it ?

As a biginner of tensorflow, I have meet some problem with your code.
by "python train.py",I get raceback (most recent call last):
File "", line 1, in
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1029, in concat
dtype=dtypes.int32).get_shape(
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 637, in convert_to_tensor
as_ref=False)
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 702, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 110, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 99, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/home/abc/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 367, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/home/abc/anaconda2/lib/python2.7/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.

Using adding problem as example, when define the model:
x_step = [:i:] be shape(1, max_steps, num_classes), h be shape(bach_size, num_cells),
can we do tf.concat with these two components?