ViCCo-Group / thingsvision

Python package for extracting representations from state-of-the-art computer vision models

Home Page:https://vicco-group.github.io/thingsvision/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Custom models

LukasMut opened this issue · comments

Allow a user to add their own (pretrained) models without the necessity to upload them to thingsvision / make a PR

  • pass a model object to the extractor class rather than a string for the model name (as is required now)

Implemented in #69 , but tests are still missing.

We have to add unittests. They are not implemented yet.

@andropar I think this is an issue we want to tackle next.