Issue with tensorflow variable names about prettytensor HOT 7 CLOSED

In the latest version that I try, I don't get that error. I can reproduce it if I put everything in a namescope and call it twice.

This is a limitation of how name_scopes and variable_scopes work together and is is recommended to prefer variable_scope when you are creating sub-graphs with variables (which all the layers do).

If you are using an interactive shell like jupyter, I find using an explicit graph when playing around (e.g. with tf.Graph().as_default():) really helps cut down on interference type errors.

from prettytensor.

I think the problem was that the variable scope was not set properly in scopes.var_and_name_scope().

I applied the following change to get everything working:

diff --git a/prettytensor/scopes.py b/prettytensor/scopes.py
index 809b32a..d1a914e 100644
--- a/prettytensor/scopes.py
+++ b/prettytensor/scopes.py
@@ -69,7 +69,8 @@ def var_and_name_scope(names):
               initializer=old_vs.initializer)

         vs_key[0].name_scope = scope
-        yield scope, vs_key[0]
+        with tf.variable_scope(vs_key[0]):
+          yield scope, vs_key[0]
       finally:
         vs_key[0] = old_vs

Now the variables have properly scoped names like "fully_connected/weights" instead of just "weights".

I am using TensorFlow 0.7.1

from prettytensor.

I had the same error when I rebase to 0.8.0. @fftobiwan 's fix also works for me.

from prettytensor.

Thanks for the update. It appears that a certain change has landed, so I will upload with the fix.

from prettytensor.

I've made the update -- this was related to changes in the semantics of tf.get_collection() and tf.get_collection_ref().

Please verify that it works, thanks again!

from prettytensor.

It works for me, thank you very much.

from prettytensor.

Zoe from stackOverflow said:
tf.reset_default_graph()
at the beginning of the script.
Worked for me. Thanks,

from prettytensor.