datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
invasive_plants_hawaii
Dataset Card for Invasive Plants Project
This dataset is aimed at the image multi-classification and segmentation of various leaf damage types caused by biocontrol agents. The dataset contains images of both the dorsal and ventral side of Clidemia Hirta leaves, that were all collected in January 2025 near Hilo (Hawaii), in dirt trails along Steinback Highway. Clidemia Hirta is a highly invasive plant on the island of Hawaii (Big Island).
Dataset Configurations and… See the full description on the dataset page: https://huggingface.co/datasets/imageomics/invasive_plants_hawaii.PlantVillage
PlantVillage Dataset
The PlantVillage Dataset is an open access repository of 54,306 images of healthy and diseased plant leaves, collected to advance research in automated plant disease diagnosis. It covers 14 crop species and 26 diseases.
This dataset was introduced in the paper "Using Deep Learning for Image-Based Plant Disease Detection" by Mohanty et al. (2016).
Quick Start
The dataset comes with pre-defined 80/20 train/test splits that preserve the leaf grouping… See the full description on the dataset page: https://huggingface.co/datasets/mohanty/PlantVillage.PlantWild
Dataset Card for PlantWild
This is a FiftyOne dataset with 30030 samples.
Installation
If you haven't already, install FiftyOne:
pip install -U fiftyone
Usage
import fiftyone as fo
from fiftyone.utils.huggingface import load_from_hub
# Load the dataset
# Note: other available arguments include 'max_samples', etc
dataset = load_from_hub("Voxel51/PlantWild")
# Launch the App
session = fo.launch_app(dataset)
Dataset Details… See the full description on the dataset page: https://huggingface.co/datasets/Voxel51/PlantWild.plant-pathology-2021
Description
Dataset from the Plant Pathology 2021 (FGVC8) Challenge.
'
For Plant Pathology 2021-FGVC8, we have significantly increased the number of foliar disease images and added additional disease categories. This year’s dataset contains approximately 23,000 high-quality RGB images of apple foliar diseases, including a large expert-annotated disease dataset. This dataset reflects real field scenarios by representing non-homogeneous backgrounds of leaf images taken at… See the full description on the dataset page: https://huggingface.co/datasets/timm/plant-pathology-2021.plant_image_degradation
Plant Disease Degradation 224
Dataset Summary
This dataset contains 224×224 plant disease images and their synthetically degraded variants for image-classification and robustness experiments. It is designed for transfer-learning workflows that require a fixed input size of 224×224 while still exposing models to realistic quality issues that occur in field capture.
The degraded images are generated from clean plant-leaf images using a field-oriented degradation… See the full description on the dataset page: https://huggingface.co/datasets/kunley2/plant_image_degradation.plantvillage-full
PlantVillage (full)
A curated re-release of the PlantVillage plant-disease image dataset
(Mohanty, Hughes, Salathé 2016), with structured per-image metadata and
a leaf-grouped train/test split. Built for the iResearch Institute 2026
Virtual Lab mentorship's Rationale 2 track. The companion debug-grade
subset is at
geraldmc/plantvillage-tiny.
What's in this dataset
54,304 images of plant leaves, photographed against plain backgrounds
under controlled lighting, across… See the full description on the dataset page: https://huggingface.co/datasets/geraldmc/plantvillage-full.deBary
Dataset Card for Dataset Name
Overview
Repository for the deBary plant disease dataset with train/test splits (85%/15%) proposed in [TBD].
Summary
Images: 9,454 JPG files
Train images: 6,065
Test images: 3,389
Species folders: 81
Health statuses: healthy, diseased
Condition labels: 1,265
Climate CSV rows: 70,999
Image Layout
deBary/
├── data/
│ ├── train/
│ │ └── <species>/<health_status>/<condition>/*.jpg
│ └── test/
│… See the full description on the dataset page: https://huggingface.co/datasets/deep-plants/deBary.PlantInquiryVQA
PlantInquiryVQA — Thinking Like a Botanist
Benchmark and framework for multi-turn, intent-driven visual question answering in plant pathology.
Accepted at ACL 2026 Findings.
Overview
PlantInquiryVQA formalises diagnostic reasoning in plant pathology as a Chain-of-Inquiry (CoI) — an ordered sequence of visually-grounded questions that adapts to the plant's severity and the expert's epistemic intent (Diagnosis / Prognosis / Management).
The benchmark evaluates… See the full description on the dataset page: https://huggingface.co/datasets/SyedNazmusSakib/PlantInquiryVQA.Plant-Diseases-PlantVillage-Dataset
Dataset Card for Dataset Name
Train and Test (20%) splits for the PlantVillage-Dataset on the subject of plant disease
@article{Mohanty_Hughes_Salathé_2016,
title={Using deep learning for image-based plant disease detection},
volume={7},
DOI={10.3389/fpls.2016.01419},
journal={Frontiers in Plant Science},
author={Mohanty, Sharada P. and Hughes, David P. and Salathé, Marcel},
year={2016},
month={Sep}}
Dataset Details
Dataset Description
Curated by: [More… See the full description on the dataset page: https://huggingface.co/datasets/BrandonFors/Plant-Diseases-PlantVillage-Dataset.plantNaturalist500k
Dataset Card for plantNaturalist-500k
Dataset Description
Dataset Summary
plantNaturalist-500k is a large-scale dataset for in-the-wild plant species classification, real-world environments.
It contains 500,909 images spanning 2,491 plant species, sampled from iNaturalist Research-grade Observations.
The dataset is specifically designed to serve as a benchmark for evaluating plant classification models in real-world scenarios, complementing existing… See the full description on the dataset page: https://huggingface.co/datasets/anhaltai/plantNaturalist500k.PlantVillage_datasetplantdoc-full
PlantDoc — full variant
A curated mirror of the PlantDoc plant disease classification dataset (Singh et al. 2020), with normalized class metadata and a stable schema, hosted as a Hugging Face Dataset for reproducible distribution. The companion plantdoc-tiny variant is a 164-image stratified subsample of this dataset for fast test-suite use.
PlantDoc was built to address a specific failure mode in earlier plant disease datasets like PlantVillage: lab-condition images don't predict… See the full description on the dataset page: https://huggingface.co/datasets/geraldmc/plantdoc-full.ne_plant_classes
NE Plant Classes
Plant photographs from the iNaturalist open data
archive, filtered to a New England bounding box (latitude 41 to 48, longitude
-74 to -67) and each labelled by a vision language model with the kind of
subject it depicts.
Labels come from Qwen/Qwen3.5-9B;
they are model output, not human annotation, and have not been checked against
a hand-labelled sample.
151,945 images in a single train split.
Columns
image - the photograph, embedded in the… See the full description on the dataset page: https://huggingface.co/datasets/blambert/ne_plant_classes.plant-pathology-2021
Description
Dataset from the Plant Pathology 2021 (FGVC8) Challenge.
'
For Plant Pathology 2021-FGVC8, we have significantly increased the number of foliar disease images and added additional disease categories. This year’s dataset contains approximately 23,000 high-quality RGB images of apple foliar diseases, including a large expert-annotated disease dataset. This dataset reflects real field scenarios by representing non-homogeneous backgrounds of leaf images taken at different… See the full description on the dataset page: https://huggingface.co/datasets/wuhuhuhu123/plant-pathology-2021.PlantVillage-Original
مجموعة بيانات PlantVillage (الصور الملونة الأصلية)
📌 نبذة تعريفيّة عن المستودع
يحتوي هذا المستودع على الصور الملونة الأصلية والمصنفة بعناية من مجموعة بيانات PlantVillage العالمية، والتي تم تخصيصها لتكون النواة الأساسية لتدريب نماذج الذكاء الاصطناعي في مشروع التخرج: "الخبير الزراعي اليمني الذكي".
يهدف هذا المشروع إلى توفير نظام خبير يعمل دون اتصال بالإنترنت (Offline) لتشخيص أمراض وآفات المحاصيل الاستراتيجية (مثل الطماطم والبطاطس وغيرها) لمساعدة المزارعين في… See the full description on the dataset page: https://huggingface.co/datasets/Omarrs11/PlantVillage-Original.plant-seedlings-dataset
Plant Seedlings Dataset
Image dataset of 12 species of plant seedlings for classification tasks. Originally from the Plant Seedlings Classification Kaggle competition.
Dataset Structure
train/ — 4,750 labeled images organized by species folder
test/ — 794 unlabeled images for submission
sample_submission.csv
Labels.csv
Species (12 classes)
Black-grass (263)
Charlock (390)
Cleavers (287)
Common Chickweed (611)
Common wheat… See the full description on the dataset page: https://huggingface.co/datasets/Khalid-Hamad/plant-seedlings-dataset.plant_doc_classification
Plant Doc Classification
A dataset for disease classification of various plants. The dataset contains 2,569 images across 28 classes:Images per class:
Apple Scab Leaf: 93
Apple leaf: 91
Apple rust leaf: 88
Bell_pepper leaf: 61
Bell_pepper leaf spot: 71
Blueberry leaf: 114
Cherry leaf: 57
Corn Gray leaf spot: 68
Corn leaf blight: 191
Corn rust leaf: 116
Peach leaf: 111
Potato leaf early blight: 116
Potato leaf late blight: 105
Raspberry leaf: 119
Soyabean leaf: 65
Squash Powdery… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/plant_doc_classification.ne_plant_photos
NE Plant Photos
Plant photographs from the iNaturalist open data
archive, filtered to a New England bounding box (latitude 41 to 48, longitude
-74 to -67), each labelled with the species it records and where it was
observed.
This is the nature portion of
blambert/ne_plant_classes -
photos a vision language model judged to show a plant in the field, rather than
a person, a microscope image, or something manmade - so photos of people and
indoor shots are largely gone, but the… See the full description on the dataset page: https://huggingface.co/datasets/blambert/ne_plant_photos.bd-crop-vegetable-plant-disease-dataset
🌾 Bangladesh Multi-Crop Disease Classification Dataset
📖 Dataset Description
This comprehensive dataset contains 123,588 images across 94 disease classes from 13 different crops commonly cultivated in the Bangladeshi agricultural region. The dataset is specifically curated to address plant disease identification challenges in South Asian agriculture, with a focus on crops that are economically and nutritionally significant to Bangladesh and the broader region.The… See the full description on the dataset page: https://huggingface.co/datasets/Saon110/bd-crop-vegetable-plant-disease-dataset.plantvillage-tiny
PlantVillage (tiny)
This is a debug-grade subset, not a faithful subsample for analysis.
50 images per class drawn from the full PlantVillage dataset is too few
to represent class-level visual diversity. Use it for iterating on
training-loop code, smoke-testing pipelines, or any situation where you
want the data structure but not the data scale. For actual classifier
training or evaluation, use
geraldmc/plantvillage-full.
What's in this dataset
A stratified subsample… See the full description on the dataset page: https://huggingface.co/datasets/geraldmc/plantvillage-tiny.SIMPDV1_plant_classification
SIMPDV1 Plant Classification
A dataset for classification of medicinal plants in South India. The dataset contains 2,513 images across 20 classes: Abutilon Indicum, Aloe barbadensis miller, Calotropis gigantea, Canna indica, Cissus quadrangularis, Curcuma longa, Eclipta prostrate, Eichhornia Crassipes, Hibiscus Rosasinensis, Ixora coccinea, Justica adhatoda, Murraya koenigii, Ocimum tenuiflorum, Ouretlanata, Phyllanthus amarus, Ricinus communis, Senna Atriculata, Sesbania… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/SIMPDV1_plant_classification.Indian-plant-leaves-species
Indian Plant Leaves Species
Dataset Summary
This dataset consists of 592 high-resolution images of leaves from 12 different plant species. All images were captured using a mobile phone camera under natural lighting conditions. The dataset is intended for use in plant species classification, leaf recognition, and related computer vision tasks.
Supported Tasks and Leaderboards
Image Classification
Species Recognition
Transfer Learning for Plant Identification… See the full description on the dataset page: https://huggingface.co/datasets/avaishnav/Indian-plant-leaves-species.AGM
Dataset Card for AGM Dataset
Dataset Summary
The AGM (AGricolaModerna) Dataset is a comprehensive collection of high-resolution RGB images capturing harvest-ready plants in a vertical farm setting. This dataset consists of 972,858 images, each with a resolution of 120x120 pixels, covering 18 different plant crops. In the context of this dataset, a crop refers to a plant species or a mix of plant species.
Supported Tasks
Image classification: plant phenotyping… See the full description on the dataset page: https://huggingface.co/datasets/deep-plants/AGM.plantseg-lookalike
PlantSeg Subtle Disease Look-Alike Pairs
A benchmark of 38,239 subtle, visually confusable plant-disease image pairs mined
from PlantSeg v3. Each pair shows two
different diseases on the same crop and the same plant organ whose appearance is
genuinely hard to tell apart — and every single pair is web-verified: it ships a
verbatim "looks-alike" quote from a cited, live source confirming the two diseases are
actually confused in the agronomic literature.
Useful for studying… See the full description on the dataset page: https://huggingface.co/datasets/tirtho149/plantseg-lookalike.plant_leaf_disease_classification
Plant Leaf Disease Classification
A dataset for disease classification of leaves from Bitter Gourd, Bottle Gourd, Tomato, Eggplant, Cauliflower, and Cucumber. The dataset contains 12,786 images across 16 classes:Images per class:
Anthracnose: 601
Anthracnose lesions: 535
Black Rot: 560
Downey mildew: 1,254
Downy mildew: 1,076
Eggplant Cercopora leaf spot: 723
Eggplant begomovirus: 720
Eggplant fresh leaf: 771
Eggplant verticillium wilt: 730
Fresh leaf: 2,122
Fusarium wilt: 502… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/plant_leaf_disease_classification.power-plant-satellite-imagery-dataset-mirror
Power Plant Satellite Imagery Dataset — Figshare mirror
This repository is an unmodified file mirror of version 1 of the Figshare
record Power Plant Satellite Imagery Dataset.
Figshare remains the canonical source. This mirror is provided for easier access from
Hugging Face tooling; it is not a new dataset release and is not affiliated with or
endorsed by the original authors.
The original dataset contains satellite imagery for 4,454 United States power plants:
1 m four-band… See the full description on the dataset page: https://huggingface.co/datasets/sarkarghya/power-plant-satellite-imagery-dataset-mirror.medicinal_plant_classification_bd
Medicinal Plant Classification Bd
This dataset contains real RGB images of medicinal plants native to Bangladesh, captured in a controlled laboratory environment. Images were collected using handheld smartphones during the summer months (July to August), providing a diverse and standardized representation of plant specimens under consistent lighting and background conditions. The dataset contains 5,000 images across 10 classes: Bohera, Devilbackbone, Haritoki, Lemongrass… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/medicinal_plant_classification_bd.DIMPSAR_medicinal_plant_classification
Dimpsar Medicinal Plant Classification
A dataset for variety classification of medicinal plants. The dataset contains 5,945 images across 40 classes:Images per class:
Aloevera: 164
Amla: 146
Amruta_Balli: 146
Arali: 146
Ashoka: 146
Ashwagandha: 146
Avacado: 146
Bamboo: 146
Basale: 146
Betel: 151
Betel_Nut: 146
Brahmi: 146
Castor: 160
Curry_Leaf: 146
Doddapatre: 146
Ekka: 146
Ganike: 115
Gauva: 146
Geranium: 146
Henna: 150
Hibiscus: 165
Honge: 146
Insulin: 146
Jasmine: 187… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/DIMPSAR_medicinal_plant_classification.plant_species
Dataset Card for "plant_species"
More Information needed
plant_village_classification
Plant Village Classification
A dataset for image classification of Plant Village Classification. The dataset contains 55,448 images across 39 classes:Images per class:
Apple___Apple_scab: 630
Apple___Black_rot: 621
Apple___Cedar_apple_rust: 275
Apple___healthy: 1,645
Background_without_leaves: 1,143
Blueberry___healthy: 1,502
Cherry___Powdery_mildew: 1,052
Cherry___healthy: 854
Corn___Cercospora_leaf_spot Gray_leaf_spot: 513
Corn___Common_rust: 1,192… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/plant_village_classification.