Skip to content

How to get embeddings using our own trained model on custom dataset #86

Description

@mahaling

I trained on a custom dataset using the train.py script and got a model saved.

But I am getting an error loading this checkpoint by following the example provided in this repo.

Can you please provide a simple code snippet to load this checkpoint and then use that to get embeddings and projections. Thanks

Loading the checkpoint throws unexpected keys in the state dict.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions