Skip to content

Adjusting to a larger dataset #64

Description

@rorycochrane

I was able to successfully replicate the model with the suggested dataset, but I'm having trouble getting equivalent results with a larger dataset.

Are there any parameters that should be adjusted when training with a larger dataset? I'm trying to train on a dataset with ~3.2k labelled images, and eventually 5k once I finish labelling the rest of them.

Thanks in advance.

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