Skip to content

Consider uring onnx for models instead of joblib #19

Description

@MikeLippincott

Something about seeing these joblib files made me wonder if it could be helpful to switch to onnx format sometime and explore the possibilities. You could use sklearn-onnx to implement the models and perhaps onnxruntime to run the models. There could be performance and other benefits to making this shift. Hat tip to @MattsonCam, who mentioned ONNX to me a bit ago.

Originally posted by @d33bs in #17 (comment)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions