usage of 'range' in 'reduce_max' and 'reduce_sum' needs to be debugged

[roomo7time]

vat_tf/vat.py

Line 34 in c5125d2

d /= (1e-12 + tf.reduce_max(tf.abs(d), range(1, len(d.get_shape())), keep_dims=True))

In tensorflow (1.8>) with python 3, this line does not seem to work. It seems range needs to be wrapped by 'list'.

[marcosly]

vat_tf/vat.py

Line 34 in c5125d2

d /= (1e-12 + tf.reduce_max(tf.abs(d), range(1, len(d.get_shape())), keep_dims=True))
In tensorflow (1.8>) with python 3, this line does not seem to work. It seems range needs to be wrapped by 'list'.

did you fix the bug?

[seansaito]

Dictionary operations should be fixed as well:

vat_tf/train_semisup.py

Line 180 in c5125d2

for key, _ in losses_eval_train.iteritems():

iteritems() should be changed to items(). Also values() in the lines below should be wrapped in list() as well.

[SiyuWang15]

I used
[i for i in range(1, len(d.get_shape())]
to replace it and worked well