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

pass image in memory to predict API for image classification #268

Closed
Felix-N opened this issue Apr 3, 2019 · 5 comments
Closed

pass image in memory to predict API for image classification #268

Felix-N opened this issue Apr 3, 2019 · 5 comments
Labels
feature New feature or request

Comments

@Felix-N
Copy link

Felix-N commented Apr 3, 2019

Is it possible to pass image(s) for classification prediction via API without writing them to the hard drive first?

@w4nderlust
Copy link
Collaborator

@Felix-N at the moment you can't, it's a limitation, I know, but we are working on a way around that, stay tuned.

@w4nderlust w4nderlust added the feature New feature or request label Apr 3, 2019
@carlogrisetti
Copy link
Contributor

@w4nderlust Do you have any hints on how this could be implemented and\or you already are working on something similar that can be helped upon?

It's basically the only missing feature (along with the unability to export models, but this will hopefully be added as a side effect of the TF2 porting) that forces me to go traditional TF\Keras on some projects.

Thanks!

@w4nderlust
Copy link
Collaborator

It took a while from the original request, but PR #1174 addresses this issue, closing it, please let us know if this works for you @Felix-N .

Ludwig Development automation moved this from Feature Requests to Done May 23, 2021
@w4nderlust
Copy link
Collaborator

@carlogrisetti this should be a welcome feature for you too I believe ;)

@carlogrisetti
Copy link
Contributor

It most definitely is!
Gonna test it as soon as I can :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature New feature or request
Projects
Development

No branches or pull requests

3 participants