Implementation:Open compass VLMEvalKit ImageCaptionDataset

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Image Captioning

Overview

Benchmark dataset implementation for COCO Caption evaluation in VLMEvalKit.

Description

ImageCaptionDataset inherits from ImageBaseDataset and implements the COCO caption benchmark for image captioning evaluation. The TYPE field is set to 'Caption'. It includes a COCO_Caption_Scorer using BLEU, ROUGE-L, and CIDEr metrics.

Usage

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

Code Reference

Source: vlmeval/dataset/image_caption.py, Lines: L1-75
Import: from vlmeval.dataset.image_caption import ImageCaptionDataset

Signature:

class ImageCaptionDataset(ImageBaseDataset):
    TYPE = 'Caption'
    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('COCO_VAL')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment