run in version 1.2.1

[xieexiaotuzi]

Hi . thank u so much for your code about rnn. I want to run it in version 1.2.1. After some changes, I meet with an error which seems a little hard for me.

code:
self._initial_state = cell.zero_state(self.batch_size,dtype=tf.float32)
error:
TypeError: int() argument must be a string or a number, not 'Variable'
I know why this happens. but due to code structure, I won't change the type of batch_size. So what should I do? thank u.

[luchi007]

sorry that I'm little busy these days, I didn't see your whole code, but I guess that you may pass a Variable type to self.batch_size, however, self.batch_size should be int type here. @xieexiaotuzi

[joyandfun]

I have the same problem.

[zhuchenxi]

I have the same problem, too.

[Domi-Zhang]

It would work for tf==1.4 that take 2 changes as following:

1. change self.batch_size to config.batch_size
2. add break condition in data_utils.batch_iter :
   ...
if end_index - start_index < batch_size:
break
return_x = x[start_index:end_index]
...