Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

ValueError: Variable d_h0_conv/w/Adam/ does not exist

See original GitHub issue

when running on mnist dataset, I got this error. ValueError: Variable d_h0_conv/w/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope? Can you help me to explain it?

Thanks

Issue Analytics

State:
Created 7 years ago
Comments:5 (2 by maintainers)

Top GitHub Comments

6reactions

chihyaomacommented, Dec 21, 2016

@carpedm20 Can you please elaborate a little bit about what exactly is the problem? I can see that the main changes are basically using tf.variable_scope() for discriminator and generator.

with tf.variable_scope("discriminator") as scope:
    scope.reuse_variables()

with tf.variable_scope("generator") as scope: 
    scope.reuse_variables()

I faced the same issue in using improved-gan, but as a beginner for TensorFlow, I found out that it’s not as straightforward as I thought. I am still trying to figure out how to solve it in the improved-gan repository. Any additional information will be a huge help to me!

0reactions

awonderfullifecommented, Oct 31, 2017

Thanks for your sharing~@FlyingTourist, it helps a lot