-
Notifications
You must be signed in to change notification settings - Fork 4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Embed metadata in exported model #1770
Comments
I thought it'd be easier to add this to the graph as a constant node, but I can't figure out how to coax the freezing process into keeping the constants in the resulting graph, so I'm removing this from the v0.4 release. I think the easiest solution for this would be to use protobuf directly to edit the output frozen graph. Not sure if it's worth the effort. |
Trying again with an alternative approach, using protobuf but with messages built-in to TensorFlow, so minimal effort. |
For the TFLite model there's no easy solution right now. The model file has a description field that's currently unused, but the TFLite converter API doesn't expose it, so it's not easy to use. For now I'll focus on the protobuf model since that's what we run the prod tests with. |
Fixed in #1919. |
This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs. |
The text was updated successfully, but these errors were encountered: