Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Open compass VLMEvalKit OlmOCRBench Tests

From Leeroopedia
Field Value
source VLMEvalKit
domain Vision, Benchmarking, OCR, PDF Testing

Overview

Test framework module defining PDF document test types for the olmOCRBench evaluation pipeline in VLMEvalKit.

Description

This utility file does not define a dataset class. It defines the comprehensive test framework for olmOCRBench evaluation including TestType and TestChecked enums, data classes like TableData, and multiple test implementation classes. Key test classes include TextPresenceTest for verifying text extraction, TextOrderTest for checking text ordering, TableTest for table structure validation, BaselineTest for baseline comparisons, and MathTest for mathematical formula recognition testing.

Usage

Imported by the olmOCRBench evaluation pipeline to define and execute document parsing tests.

Code Reference

  • Source: vlmeval/dataset/olmOCRBench/tests.py, Lines: L1-1187
  • Import: from vlmeval.dataset.olmOCRBench.tests import *

Key Classes:

class TableData:
    ...

class TestType(str, Enum):
    ...

class BasePDFTest:
    ...

class TextPresenceTest(BasePDFTest):
    ...

class TextOrderTest(BasePDFTest):
    ...

class TableTest(BasePDFTest):
    ...

class MathTest(BasePDFTest):
    ...

I/O Contract

Direction Description
Inputs PDF document parsing outputs and test specifications
Outputs Test results with pass/fail status and detailed scoring

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment