Implementation:Open compass VLMEvalKit ChartQAPro

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Chart QA

Overview

Benchmark dataset implementation for ChartQAPro evaluation in VLMEvalKit.

Description

ChartQAPro inherits from ImageBaseDataset and implements the ChartQA Pro benchmark for evaluating chart question answering with support for Direct, Chain-of-Thought (CoT), and Program-of-Thought (PoT) modes. The TYPE field is set to 'VQA'.

Usage

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

Code Reference

Source: vlmeval/dataset/chartqapro.py, Lines: L1-126
Import: from vlmeval.dataset.chartqapro import ChartQAPro

Signature:

class ChartQAPro(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('ChartQAPro')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment