Skip to content

Conversation

AustinT
Copy link

@AustinT AustinT commented Apr 14, 2018

I found that in your example code, you loaded the model, then ran the variable initialisation, which effectively erased the loaded model. I changed the code to load the model after initialisation to avoid this problem. I hope you accept this change.

I was running this on tensorflow 1.7, so it is possible that this behaviour didn't exist in previous versions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant