Wheat Disease Detection Images from Yuanyang, Henan, China: 4,156 Field Photos with Bounding Boxes across 7 Classes (AgML Mirror)

Provider
Chaowei Ma et al.; Hugging Face mirror by Project-AgML
License
CC-BY-4.0 (source)
Size
5 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/Project-AgML/wheat_disease_detection)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.15621359
Category
Agriculture & Environment
Source
https://huggingface.co/datasets/Project-AgML/wheat_disease_detection

About this dataset

Field RGB images of wheat in Yuanyang, Henan Province, China, from the 2023 season, taken with smartphones and DSLR cameras, with bounding boxes for wheat disease symptoms across seven categories. After removing duplicates the authors split the set 8:1:1 into 3,359 training, 377 validation and 420 test images. Released with a paper on lightweight wheat disease detection with an improved YOLOv8 (Transactions of the Chinese Society of Agricultural Engineering 40, 2024, 187 to 195). This mirror holds 4,156 images with 5,845 boxes. Useful for wheat disease detection, crop protection scouting apps and lightweight detectors. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/wheat_disease_detection") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Chaowei Ma et al. et al. and the DOI 10.5281/zenodo.15621359.

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("Project-AgML/wheat_disease_detection")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: data/train-00000-of-00003.parquet

Analyze this dataset without downloading it

On Scigantic, Wheat Disease Detection Images from Yuanyang, Henan, China: 4,156 Field Photos with Bounding Boxes across 7 Classes (AgML Mirror) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Agriculture & Environment datasets