Skip to content

Missing Model Folders  #2

@vkhup

Description

@vkhup

I am currently using the enzymeNER package for a project and have encountered some confusion regarding the expected folder structure and file handling during model training and inference.

In particular, I noticed that the script attempts to save model data in directories such as BioBertModels or SciBertModels along with a run_id. However, these directories do not seem to exist by default in the package, and I am unsure if they are supposed to be created automatically, if I need to create them manually, or if I am possibly misunderstanding the intended workflow.

Could you please clarify:

Are the BioBertModels and SciBertModels directories supposed to be created manually by the user, or are they generated by the script during the training process?
Is there a specific folder structure that needs to be in place before running the training or inference scripts?
Am I missing any critical setup steps that might explain the errors related to missing folders or files?

Is there any more in depth tutorial to use enzymeNER as I am relatively new to using programming and wanted to integrate this to my dissertation in bioinformatics.

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