Implementation:Open compass VLMEvalKit SFE

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Science Education

Overview

Benchmark dataset implementation for SFE evaluation in VLMEvalKit.

Description

SFE inherits from ImageVQADataset and implements the SFE benchmark for science and education evaluation. It inherits the TYPE 'VQA' from its parent class. It supports English (SFE) and Chinese (SFE-zh) variants with discipline-specific MCQ prompts.

Usage

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

Code Reference

Source: vlmeval/dataset/sfebench.py, Lines: L1-220
Import: from vlmeval.dataset.sfebench import SFE

Signature:

class SFE(ImageVQADataset):
    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('SFE')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment