Implementation:Open compass VLMEvalKit OlmOCRBench

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, OCR, Document Parsing

Overview

Benchmark dataset implementation for olmOCRBench evaluation in VLMEvalKit.

Description

olmOCRBench inherits from ImageBaseDataset and implements the olmOCR benchmark for document parsing evaluation. The TYPE field is set to 'QA'. It uses a system prompt for natural plain text representation with LaTeX notation for math and Markdown table formatting.

Usage

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

Code Reference

Source: vlmeval/dataset/olmOCRBench/olmocrbench.py, Lines: L1-54
Import: from vlmeval.dataset.olmOCRBench.olmocrbench import olmOCRBench

Signature:

class olmOCRBench(ImageBaseDataset):
    TYPE = 'QA'
    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('olmOCRBench')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment