Can you please update the implementation to use tf.GraphKeys.GLOBAL_VARIABLES, to match the default TensorFlow implementation, or suggest a workaround? Thanks!
Thanks for the bug, some of the changes in v0.12 were not backwards compatible and so I needed to cut a new release. Please reopen if the latest version in pypi doesn't work.
This question on Stack Overflow observes that using Pretty Tensor with the latest version of TensorFlow will lead to uninitialized variable errors. As far as I can tell, the problem stems from using
tf.GraphKeys.VARIABLES
as the default variable collection, which doesn't work with the (new) recommended way to initialize all variables (tf.global_variables_initializer()
.Can you please update the implementation to use
tf.GraphKeys.GLOBAL_VARIABLES
, to match the default TensorFlow implementation, or suggest a workaround? Thanks!