Implementation:Open compass VLMEvalKit EMMADataset

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Multi-modal Assessment

Overview

Benchmark dataset implementation for EMMA evaluation in VLMEvalKit.

Description

EMMADataset inherits from ImageShortQADataset and implements the EMMA benchmark for multi-modal assessment. It inherits the TYPE 'Short' from its parent class. It supports both MCQ and open-ended formats with optional Chain-of-Thought instruction.

Usage

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

Code Reference

Source: vlmeval/dataset/emma.py, Lines: L1-56
Import: from vlmeval.dataset.emma import EMMADataset

Signature:

class EMMADataset(ImageShortQADataset):
    TYPE = 'Short'
    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('EMMA')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment