make_template('shared_model',model)

[EricKani]

Hi,
I have a question about shared_model = tf.make_template('shared_model', model) in line 104 in the VDSR.py. Is this operation have some advantages? thank you very much!
And the second question is whether the way of data_reading in your code can replace the way of tfrecords?

[EricKani]

Hi,
The first question I think I have solved it. "tf.make_template" is used for the variable sharing, like using "with the tf.variable_scope( ' ', reuse = True)".
Is that right?

[Jongchan]

@EricKani Yes, that is correct!