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

[Feature request] with_session_from_memory support #29

Open
kipcole9 opened this issue May 13, 2024 · 3 comments
Open

[Feature request] with_session_from_memory support #29

kipcole9 opened this issue May 13, 2024 · 3 comments

Comments

@kipcole9
Copy link

In working on a segment-anthing livebook, based upon this forum example, I am downloading the onnx model from hugging face. The benefit is that the Livebook can be readily shared with no dependencies.

Currently it needs to be saved to a file system before calling Ortext.load/1 since that function ultimately delegates to the following in model.rs:

    let session = Session::builder()?
        .with_execution_providers(&eps)?
        .with_optimization_level(map_opt_level(opt))?
        .with_model_from_file(model_path)?;

A version or an option which calls .with_model_from_memory(binary) would be a valuable, and hopefully a simple addition.

I think Livebooks is a likely a common use case so hopefully something you might consider. I would happily send a PR if I had any relevant skill, but in Rust I do not.

@mortont
Copy link
Collaborator

mortont commented May 13, 2024

Thanks for the idea! We've been planning to implement model loading from memory for a while now, but we're waiting on the upstream ort 2.0 changes to settle before doing so.

One other benefit that will unlock is loading directly from axon_onnx, so in the future we may be able to export Axon models to run with Ortex in memory.

@kipcole9
Copy link
Author

Thanks for the consideration - and the library. Feel free to close since its already on your to-do list.

@mortont
Copy link
Collaborator

mortont commented May 13, 2024

We'll keep this open to track, should be an easy add once the ort API settles

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