Implementation:Open compass VLMEvalKit DUDE

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Document Understanding

Overview

Benchmark dataset implementation for DUDE evaluation in VLMEvalKit.

Description

DUDE inherits from ImageBaseDataset and implements the DUDE benchmark for document understanding evaluation. The TYPE field is set to 'VQA'. It supports full and mini splits with per-model page handling configurations.

Usage

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

Code Reference

Source: vlmeval/dataset/dude.py, Lines: L1-211
Import: from vlmeval.dataset.dude import DUDE

Signature:

class DUDE(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('DUDE')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment