EyePACS — Diabetic Retinopathy Detection (Kaggle 2015)

~88,000 fundus images graded 0–4 for DR severity. Largest public DR dataset; competition images from EyePACS clinics.

At a glance

Field	Value
Short name	eyepacs
Full name	EyePACS — Diabetic Retinopathy Detection (Kaggle 2015)
Primary category	fundus
Contained modalities	fundus
Tasks	grading, classification
Samples	88,702
Classes	5 (No DR, Mild, Moderate, Severe, Proliferative DR)
Splits	train, test
Size	89.0 GB
Source-stated terms	Kaggle competition rules (non-commercial research)
Normalized terms	research-only
Descriptive screening label	Research or challenge restriction recorded; check source
Terms scope	challenge_participation
Access friction	self_service_clickthrough
Route backend	Kaggle
Availability	available (checked 2026-07-21)
Acquisition support	standard_platform_supported
Legacy sample-loader status	Standard loader included

Notes

Very large (~89 GB). Kaggle competition account and acceptance of rules required.

Access preflight and acquisition

CLI

# Read-only preflight
eyehub download eyepacs --data-dir ./data --dry-run --json

# Explicit transfer, only when preflight reports supported behavior
eyehub download eyepacs --data-dir ./data

Python

from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY

ds = REGISTRY.get_dataset('eyepacs')
print(preflight_dataset(ds, './data'))  # no transfer

Upstream page: kaggle.com/c

Source-term evidence: kaggle.com/c

Loader example

This entry includes a standard DatasetSample loader.

from pathlib import Path
from eyedatahub.datasets.registry import REGISTRY

data_dir = Path('~/.eyedatahub/data').expanduser()
ds = REGISTRY.get_dataset('eyepacs')
samples = ds.load(data_dir, split='test')
for s in samples[:5]:
    print(s.sample_id, s.label, s.image_path)

Citation

BibTeX

@misc{eyepacs,
  title  = { EyePACS — Diabetic Retinopathy Detection (Kaggle 2015) },
  note   = { EyePACS / California Healthcare Foundation. 'Diabetic Retinopathy Detection', Kaggle Competition, 2015 },
  year   = { 2015 },
  url    = { https://www.kaggle.com/c/diabetic-retinopathy-detection },
}

Plain text

EyePACS / California Healthcare Foundation. 'Diabetic Retinopathy Detection', Kaggle Competition, 2015.

Source-stated terms

• Raw source string: Kaggle competition rules (non-commercial research)
• Normalized category: research-only
• Apparent scope: challenge_participation
• Descriptive screening label: Research or challenge restriction recorded; check source

⚠️ Source-stated terms, scope, and normalized labels are curation metadata, not legal advice or a permission finding. Review the current official source before transfer or reuse.

Related datasets with shared modalities

• airogs: AIROGS: AI for Robust Glaucoma Screening (113,893 records, cc-by-nc-nd)
• eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records, unknown)
• justraigs: JustRAIGS: Just Referral AI Glaucoma Screening Dataset (101,442 records, cc-by-nc-nd)
• multieye: MultiEYE: OCT-Enhanced Fundus Multi-Disease Benchmark (58,036 records, mit)
• angioreport: AngioReport Fundus Angiography Report Dataset (55,361 records, unknown)
• ffa_ir: FFA-IR Medical Report Dataset (47,247 records, unknown)
• bidr: BiDR: Diabetic Retinopathy Diagnosis Dataset (35,126 records, unknown)
• dr_arranged: Diabetic Retinopathy Arranged Dataset (Tianchi 93926) (35,126 records, cc-by-nc-sa)