Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@nkaenzig
Copy link
Collaborator

@nkaenzig nkaenzig commented Oct 16, 2025

Closes #908

Building up on #912 and #914, this PR adds a a fully functional evaluation config for QuiltVQA. This is the first free-form visual question answering task in eva - using a G-Eval LLM Judge as metric.

How to test?

export GEMINI_API_KEY=<your-secret>
DATA_ROOT=/path/to/download/dataset/to DOWNLOAD_DATA=true MODEL_NAME=google/gemini-2.5-flash-lite eva test --config configs/multimodal/pathology/online/free_form/quilt_vqa.yaml
image

@nkaenzig nkaenzig self-assigned this Oct 16, 2025
@nkaenzig nkaenzig marked this pull request as ready for review October 16, 2025 12:59
Copy link
Collaborator

@MaxFeucht MaxFeucht left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, only minor comments

@nkaenzig nkaenzig enabled auto-merge (squash) October 22, 2025 07:04
@nkaenzig nkaenzig merged commit cd1c6d0 into main Oct 22, 2025
7 checks passed
@nkaenzig nkaenzig deleted the 908-add-quilt-vqa-yaml-config branch October 22, 2025 07:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add QuiltVQA dataset

2 participants