typeError with tf_mittens.py, line 168

[linflyer]

I am trying to using mittens to fit for a target domain, but met the following errors:

new_embed = mittens_model.fit(
... comatrix,
... vocab=id2word_cooc,
... initial_embedding_dict= old_embed)

Traceback (most recent call last):
File "", line 4, in
File "/home/clin/env/local/lib/python2.7/site-packages/mittens/mittens_base.py", line 84, in fit
fixed_initialization=fixed_initialization)
File "/home/clin/env/local/lib/python2.7/site-packages/mittens/tf_mittens.py", line 61, in _fit
self.cost = self._get_cost_function()
File "/home/clin/env/local/lib/python2.7/site-packages/mittens/tf_mittens.py", line 168, in _get_cost_function
if self.mittens > 0:
File "/home/clin/env/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 542, in nonzero
raise TypeError("Using a tf.Tensor as a Python bool is not allowed. "
TypeError: Using a tf.Tensor as a Python bool is not allowed. Use if t is not None: instead of if t: to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

[ndingwall]

How are you initializing mittens_model ? It looks like self.mittens has become a tf.Tensor somehow, but I might be misreading the traceback.