Skip to content
This repository has been archived by the owner on Oct 19, 2019. It is now read-only.

Output Node Names for the pre-trained data ? #29

Open
dangithubs opened this issue Mar 24, 2017 · 1 comment
Open

Output Node Names for the pre-trained data ? #29

dangithubs opened this issue Mar 24, 2017 · 1 comment

Comments

@dangithubs
Copy link

dangithubs commented Mar 24, 2017

I am trying to use Freeze_Graph.py in Tensorflow_serving on the pre-trained model listed on this page which is in .ckpt and .meta

I have tried the output node names as "Accuracy/predictions"

However this is not correct, I expect the output node names were passed into whatever trained the model. However this isn't listed in the Readme.md.

@ameliajimenez
Copy link

Hello @dangithubs

How are you loading the pre-trained weights into the model? I would like to finetune it for a different task. Thanks in advance

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

No branches or pull requests

2 participants