Implementation:Open compass VLMEvalKit ChartMuseum

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Chart Understanding

Overview

Benchmark dataset implementation for ChartMuseum evaluation in VLMEvalKit.

Description

ChartMuseum inherits from ImageBaseDataset and implements the ChartMuseum benchmark for evaluating chart understanding capabilities. The TYPE field is set to 'VQA'. It supports dev and test splits with custom prompt building and evaluation logic for chart analysis tasks.

Usage

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

Code Reference

Source: vlmeval/dataset/chartmuseum.py, Lines: L1-202
Import: from vlmeval.dataset.chartmuseum import ChartMuseum

Signature:

class ChartMuseum(ImageBaseDataset):
    TYPE = 'VQA'
    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('ChartMuseum_dev')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment