Implementation:Open compass VLMEvalKit TextMCQDataset

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Text MCQ

Overview

Benchmark dataset implementation for Text MCQ evaluation in VLMEvalKit.

Description

TextMCQDataset inherits from TextBaseDataset and implements text-only multiple-choice question evaluation. The TYPE field is set to 'MCQ'. The file also defines CustomTextMCQDataset for custom text MCQ benchmarks. It provides prompt building with options formatting and hint support.

Usage

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

Code Reference

Source: vlmeval/dataset/text_mcq.py, Lines: L1-121
Import: from vlmeval.dataset.text_mcq import TextMCQDataset

Signature:

class TextMCQDataset(TextBaseDataset):
    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('N/A')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment