Implementation:Open compass VLMEvalKit MedqbenchMCQDataset

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Medical QA, Multiple Choice

Overview

Benchmark dataset implementation for MedQ-Bench MCQ evaluation in VLMEvalKit.

Description

MedqbenchMCQDataset inherits from ImageMCQDataset and implements the MedQ-Bench MCQ benchmark for medical multiple-choice question answering. The TYPE field is set to 'MCQ'. It supports dev and test splits.

Usage

Registered in vlmeval/dataset/__init__.py and invoked through build_dataset() by benchmark name.

Code Reference

Source: vlmeval/dataset/medqbench_mcq.py, Lines: L1-211
Import: from vlmeval.dataset.medqbench_mcq import MedqbenchMCQDataset

Signature:

class MedqbenchMCQDataset(ImageMCQDataset):
    TYPE = 'MCQ'
    DATASET_URL = {...}
    DATASET_MD5 = {...}
    ...

I/O Contract

Direction	Description
Inputs	TSV dataset file with image/video paths and questions
Outputs	Evaluation results DataFrame with scores per category

Usage Examples

from vlmeval.dataset import build_dataset
dataset = build_dataset('MedqbenchMCQ_dev')

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment