Skip to content
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

Load TFJS trained model in java application. #476

Open
cmckamey opened this issue Oct 12, 2022 · 3 comments
Open

Load TFJS trained model in java application. #476

cmckamey opened this issue Oct 12, 2022 · 3 comments

Comments

@cmckamey
Copy link

cmckamey commented Oct 12, 2022

I have a model that was developed and trained in TFJS and I want to use it in my java application.

I managed to convert it to keras and then to a SavedModel but I am wondering if there is a way to just load the TFJS model directly and spare the clunky conversion process that involves several additional steps and python.

Is such a thing even possible?

@Craigacp
Copy link
Collaborator

Looks like you should be able to go directly to a TF Saved Model with the converter, but I don't think the TFJS file format is documented so we couldn't support it.

@cmckamey
Copy link
Author

Yeah I have it working very well post conversion, just wish I could save that step. Makes implementation of my project tricky.

@Craigacp
Copy link
Collaborator

Unfortunately not. At the moment it looks like tfjs uses something Keras-like as it's JSON format, but we don't have all the Python bits necessary to load in Keras models that aren't exported in SavedModel format.

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

No branches or pull requests

2 participants