Running is_train on celebA throws the error: 'Tshape' not in list of allowed values: int32, int64

I followed the installation instructions with Tensorflow 0.12.1 but when I try to train celebA dataset I get the following error. Anyone experiencing the same thing?

```
$python main.py --dataset celebA --input_height=108 --is_train --is_crop True
Traceback (most recent call last):
File "main.py", line 96, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "main.py", line 76, in main
sample_dir=FLAGS.sample_dir)
File "/home/me/my_tensorflow/gans/DCGAN-tensorflow/model.py", line 75, in __init__
self.build_model()
File "/home/me/my_tensorflow/gans/DCGAN-tensorflow/model.py", line 107, in build_model
self.G = self.generator(self.z)
File "/home/me/my_tensorflow/gans/DCGAN-tensorflow/model.py", line 359, in generator
self.z_, [-1, s_h16, s_w16, self.gf_dim * 8])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2448, in reshape
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 582, in apply_op
_Attr(op_def, input_arg.type_attr))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 60, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: DataType float32 for attr 'Tshape' not in list of allowed values: int32, int64
```

Reproduce the command from the report, then inspect main.py and model.py, especially model.py around generator line 359 where the reshape fails. Trace the shape argument into that call and verify that celebA training starts without the TensorFlow TypeError.

Written by the indexing model from the issue text.