Implementation:Open compass VLMEvalKit GOBenchDataset

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Image Generation Quality

Overview

Benchmark dataset implementation for GOBench evaluation in VLMEvalKit.

Description

GOBenchDataset inherits from ImageBaseDataset and implements the GOBench benchmark for evaluating image generation quality across reality, aesthetics, and instruction consistency. The TYPE field is set to 'GOBench_QA'.

Usage

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

Code Reference

Source: vlmeval/dataset/gobench.py, Lines: L1-206
Import: from vlmeval.dataset.gobench import GOBenchDataset

Signature:

class GOBenchDataset(ImageBaseDataset):
    TYPE = 'GOBench_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('GOBench')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment