# InvalidArgumentError while running conditioning on Edward

**URL:** <https://discourse.edwardlib.org/t/invalidargumenterror-while-running-conditioning-on-edward/1054>\
**Category:** General\
**Created:** [April 5, 2019, 9:35am UTC](https://discourse.edwardlib.org/t/invalidargumenterror-while-running-conditioning-on-edward/1054 "2019-04-05T09:35:55Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![harc007](https://avatars.discourse-cdn.com/v4/letter/h/bbce88/32.png) [@harc007](https://discourse.edwardlib.org/u/harc007)\
**Post date:** [April 5, 2019, 9:35am UTC](https://discourse.edwardlib.org/t/invalidargumenterror-while-running-conditioning-on-edward/1054/1 "2019-04-05T09:35:55Z")

</div>

Hi, I’m new to Edward and getting stuck at this issue.

```
import edward as ed
import six
import tensorflow as tf
from edward.models import Bernoulli, Beta
unknown = Beta(concentration1=1.0, concentration0=1.0)
c = Bernoulli(probs=unknown, sample_shape = 100)
cond = ed.complete_conditional(unknown)
prob_post = ed.copy(cond, {c:lit_abs}) # lit_abs is a np array with shape (100,) with 1's and 0's in it
sess.run({key:val for key, val in six.iteritems(prob_post.parameters) if isinstance(val, tf.Tensor)})

```

```
InvalidArgumentError Traceback (most recent call last)
 in ()
      2 cond = ed.complete_conditional(unknown)
      3 prob_post = ed.copy(cond, {c:np.asarray(lit_abs)})
----> 4 sess.run({key:val for key, val in six.iteritems(prob_post.parameters) if isinstance(val, tf.Tensor)})

/home/uname/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
    903 try:
    904 result = self._run(None, fetches, feed_dict, options_ptr,
--> 905 run_metadata_ptr)
    906 if run_metadata:
    907 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/uname/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1135 if final_fetches or final_targets or (handle and feed_dict_tensor):
   1136 results = self._do_run(handle, final_targets, final_fetches,
-> 1137 feed_dict_tensor, options, run_metadata)
   1138 else:
   1139 results = []

/home/uname/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1353 if handle is None:
   1354 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1355 options, run_metadata)
   1356 else:
   1357 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/home/uname/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
   1372 except KeyError:
   1373 pass
-> 1374 raise type(e)(node_def, op, message)
   1375 
   1376 def _extend_graph(self):

InvalidArgumentError: Input 0 of node copied/complete_conditional_Beta_2/1554456706.32swapback/complete_conditional_Beta_2/1554456706.32swap/conjugate_log_joint/Cast_1 was passed int64 from Const_3:0 incompatible with expected int32.
```