docling-project / docling-project/docling

Why does image annotation leave out certain images?

Open
#2,240 2 comments 0 reactions 0 assignees View on GitHub
question triage/close-stale
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

I've been experimenting with running local VLMs to generate annotations for the images of my documents, specifically I've been using the `HuggingFaceTB/SmolVLM-256M-Instruct` model.

I've noticed that not all of my images are annotated. Is this an issue with hardware, the model, or just the documents I am using? It would be of great help if anyone knows why this is.

Thank you!!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.