datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
agarwood_leaf_disease_classification
Agarwood Leaf Disease Classification
A dataset for disease classification of agarwood leaves. The dataset contains 5,472 images across 14 classes: Anthracnose, Black spots, Brown clumps, Brown spots, Downy mildew, Flea Beetles, Healthy, Mealy bugs, Mosaic Viruses, Powdery mildew, Scale insect, Sooty mold, Spiders, Translucent lesion.Images per class:
Anthracnose: 232
Black spots: 674
Brown clumps: 118
Brown spots: 1,055
Downy mildew: 674
Flea Beetles: 115
Healthy: 415
Mealy… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/agarwood_leaf_disease_classification.apple_leaf_disease_classification
Apple Leaf Disease Classification
A dataset for image classification of Apple Leaf Disease Classification. The dataset contains 7,505 images across 3 classes: Alternaria, Apple_Mosaic, Healthy.Images per class:
Alternaria: 2,523
Apple_Mosaic: 2,523
Healthy: 2,459
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{yatoo2024indigenous,
title={An indigenous dataset for the detection and classification… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/apple_leaf_disease_classification.corn-leaf-diseases-pests-and-deficiencies
Corn Leaf Diseases, Pests and Deficiencies
Dataset de imágenes de hojas de maíz para la clasificación de enfermedades, plagas y deficiencias nutricionales. Forma parte de Doctor Maíz, un sistema de diagnóstico offline pensado para pequeños agricultores de El Salvador.
Sobre este corpus se entrenó el modelo desplegado en la aplicación móvil del proyecto: EfficientNet-Lite0 cuantizado a Int8, de 3.5 MB, con macro-F1 de 0.9468 sobre un conjunto de prueba independiente de 5 015… See the full description on the dataset page: https://huggingface.co/datasets/daiv05/corn-leaf-diseases-pests-and-deficiencies.corn_leaf_pest_classification
Corn Leaf Pest Classification
A dataset for image classification of Corn Leaf Pest Classification.The raw dataset contains 1,308 images.The augmented dataset contains 11,772 images.
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{tchokogoue2025towards,
title={Towards precision agriculture: A dataset for early detection of corn leaf pests},
author={Tchokogou{\'e}, Thierry and Noumsi, Auguste… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/corn_leaf_pest_classification.tomato_leaf_disease
Tomato Leaf Disease
A dataset for image classification of Tomato Leaf Disease. The dataset contains 11,000 images across 10 classes: Bacterial Spot, Early Blight, Healthy, Late Blight, Leaf Mold, Septoria Leaf Spot, Spider Mites Two-spotted Spider Mite, Target Spot, Tomato Mosaic Virus, Tomato Yellow Leaf Curl Virus.Images per class:
Bacterial Spot: 1,100
Early Blight: 1,100
Healthy: 1,100
Late Blight: 1,100
Leaf Mold: 1,100
Septoria Leaf Spot: 1,100
Spider Mites Two-spotted… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/tomato_leaf_disease.papaya_leaf_disease_classification_bangladesh
Papaya Leaf Disease Classification Bangladesh
A dataset for disease classification of Papaya leaves. The dataset contains raw and augmented versions.The raw dataset contains 1,400 images.Images per class:
Healthy Leaf: 182
Leaf Curl: 284
Mealybug: 233
Mite Disease: 243
Mosaic: 214
Ring Spot: 244
The augmented dataset contains 6,618 images.Images per class:
Healthy Leaf: 879
Leaf Curl: 1,334
Mealybug: 1,096
Mite Disease: 1,149
Mosaic: 1,009
Ring Spot: 1,151
This dataset is… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/papaya_leaf_disease_classification_bangladesh.LeafCondition
AutoTrain Dataset for project: leaf
Dataset Description
This dataset has been automatically processed by AutoTrain for project leaf.
Languages
The BCP-47 code for the dataset's language is unk.
Dataset Structure
Data Instances
A sample from this dataset looks as follows:
[
{
"image": "<256x256 RGB PIL image>",
"target": 4
},
{
"image": "<256x256 RGB PIL image>",
"target": 1
}]
Dataset Fields
The dataset… See the full description on the dataset page: https://huggingface.co/datasets/OttoYu/LeafCondition.tea-leaf-disease-dataset
Data
Image data is not versioned in this repository. Only manifests, audit outputs,
and fingerprints are tracked, which is enough to verify and rebuild the exact
partition used.
Layout
data/
raw/ TeaLeafBD release as downloaded (gitignored)
tea_leaf_clean/ intermediate build (gitignored)
Tea_leaf_dataset/ FINAL audited dataset (gitignored)
manifests/ tracked audit artifacts
rice_leaf_disease_classification
Rice Leaf Disease Classification
A dataset for image classification of Rice Leaf Disease Classification. The dataset contains 3,829 images across 6 classes: Bacterial_Leaf_Blight, Brown_Spot, Healthy_Rice_Leaf, Leaf_Blast, Leaf_Scald, Sheath_Blight.Images per class:
Bacterial_Leaf_Blight: 636
Brown_Spot: 646
Healthy_Rice_Leaf: 653
Leaf_Blast: 634
Leaf_Scald: 628
Sheath_Blight: 632
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/rice_leaf_disease_classification.CS-D_tea_leaf_disease_classification
Tea Leaf Disease Classification
A dataset for disease classification of tea leaves. The dataset contains 80,329 images across 6 classes: Blister_Blight, Brown_Blight, Healthy_leaves, Leaf_Red_Rust, Red_Spider_Mite, Tea_Mosquito_Bug.
Images per class:
Blister_Blight: 13,500
Brown_Blight: 13,500
Healthy_leaves: 12,829
Leaf_Red_Rust: 13,500
Red_Spider_Mite: 13,500
Tea_Mosquito_Bug: 13,500
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/CS-D_tea_leaf_disease_classification.white-cabbage-leaf-damage
White Cabbage Leaf Damage Dataset
Description
This dataset contains images of white cabbage leaves with various types of damage. It is designed for researchers and developers working on agricultural computer vision and plant pathology detection.
Dataset Structure
The dataset is organized into folders representing different classes of leaf damage or healthy states.
Usage
You can use this dataset with the datasets library:
from datasets… See the full description on the dataset page: https://huggingface.co/datasets/Arko007/white-cabbage-leaf-damage.MH_SoyaHealthVision_disease_classification_leaf
MH SoyaHealthVision Disease Classification Leaf
A dataset for disease classification of soybean leaves. The dataset contains 2,782 images across 6 classes: Caterpillar_Semilooper_Pest, Frog_Leaf_Eye, Healthy, Mosaic, Rust, Spectoria_Brown_Spot.Images per class:
Caterpillar_Semilooper_Pest: 582
Frog_Leaf_Eye: 169
Healthy: 204
Mosaic: 707
Rust: 852
Spectoria_Brown_Spot: 268
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/MH_SoyaHealthVision_disease_classification_leaf.LeafNetThe PlantVillage dataset, with over 54,000 images spanning 14 plant species and 26 disease types, has been widely used for leaf disease classification. However, it is limited in both scale and diversity. To address these limitations, we developed LeafNet, a large-scale dataset designed to support foundation models for leaf disease diagnosis. We introduce LeafNet comprises over 186,000 images from 22 crop species, covering 43 fungal diseases, 8 bacterial diseases, 2 mould (oomycete) diseases, 6… See the full description on the dataset page: https://huggingface.co/datasets/enalis/LeafNet.Matthiola-incana-Leaf-Image-Classification
Matthiola incana Leaf Image Classification dataset
Matthiola incana Leaf Image Classification(MiLIC) dataset is intended to create a model for classifying images of Matthiola incana leaves into single-flowered leaf or double-flowered leaf.
Matthiola incana
Matthiola incana, a member of the family Brassicaceae, is an ornamental plant cultivated worldwide for its beautiful flowers. This species exhibits two flower forms: single and double flowers. The market for… See the full description on the dataset page: https://huggingface.co/datasets/Kentaro-Machida/Matthiola-incana-Leaf-Image-Classification.rice_leaf_disease_classification_india
Rice Leaf Disease Classification India
A dataset for disease classification of rice leaves. The dataset contains 5,932 images across 4 classes: Bacterialblight, Blast, Brownspot, Tungro.Images per class:
Bacterialblight: 1,584
Blast: 1,440
Brownspot: 1,600
Tungro: 1,308
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{sethy2020deep,
title={Deep feature based rice leaf disease identification using… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/rice_leaf_disease_classification_india.potato_leaf_blight
Potato Leaf Blight Classification
A dataset for disease classification of Irish Potato leaves. The dataset contains 58,709 images across 3 classes: earlyblt, healthy, lateblt.Images per class:
earlyblt: 17,772
healthy: 20,438
lateblt: 20,499
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{laizer2025irish,
title={Irish potato imagery dataset for detection of early and late blight diseases}… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/potato_leaf_blight.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.arabica_coffee_leaf_disease_classification
Arabica Coffee Leaf Disease Classification
A dataset for disease classification of Arabica Coffee Leaf. The dataset contains 58,549 images across 5 classes: Cerscospora, Healthy, Leaf_rust, Miner, Phoma.Images per class:
Cerscospora: 7,681
Healthy: 18,983
Leaf_rust: 8,336
Miner: 16,978
Phoma: 6,571
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{jepkoech2021arabica,
title={Arabica coffee leaf… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/arabica_coffee_leaf_disease_classification.soybean_leaf_disease_classification
Soybean Leaf Disease Classification
A dataset for disease classification of soybean leaves. The dataset contains 1,176 images across 6 classes: Bacterial leaf Blight, Dry_leaf, Healthy, Root_images, Septoria_Brown_Spot, Vein Necrosis.Images per class:
Bacterial leaf Blight: 226
Dry_leaf: 230
Healthy: 288
Root_images: 10
Septoria_Brown_Spot: 284
Vein Necrosis: 138
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/soybean_leaf_disease_classification.DIMPSAR_medicinal_leaf_classification
DIMPSAR Medicinal Leaf Classification
A dataset for variety classification of medicinal plant leaves. The dataset contains 6,900 images across 80 classes:
Images per class:
Aloevera: 118
Amla: 67
Amruthaballi: 91
Arali: 89
Astma_weed: 82
Badipala: 76
Balloon_Vine: 61
Bamboo: 118
Beans: 97
Betel: 114
Bhrami: 104
Bringaraja: 73
Caricature: 76
Castor: 129
Catharanthus: 134
Chakte: 68
Chilly: 69
Citron lime (herelikai): 99
Coffee: 83
Common rue(naagdalli): 67
Coriender: 115
Curry:… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/DIMPSAR_medicinal_leaf_classification.potato_leaf_blight
Potato Leaf Blight Classification
A dataset for disease classification of Irish Potato leaves. The dataset contains 58,709 images across 3 classes: earlyblt, healthy, lateblt.Images per class:
earlyblt: 17,772
healthy: 20,438
lateblt: 20,499
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{laizer2025irish,
title={Irish potato imagery dataset for detection of early and late blight diseases}… See the full description on the dataset page: https://huggingface.co/datasets/ByteFox11/potato_leaf_blight.PriBel_betel_leaf_disease_classification
PriBel Betel Leaf Disease Classification
A dataset for disease classification of betel leaves. The dataset contains 1,800 images across 3 classes: Diseased, Dried, Healthy.Images per class:
Diseased: 509
Dried: 622
Healthy: 669
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{mane2025pribel,
title={PriBeL: A primary betel leaf dataset from field and controlled environment},
author={Mane, Gauri… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/PriBel_betel_leaf_disease_classification.Dhan-Shomadhan_rice_leaf_disease_classification
Dhan Shomadhan Rice Leaf Disease Classification
This dataset provides real-world RGB images of rice leaves affected by multiple disease symptoms, captured under natural agricultural conditions. It offers a practical resource for developing and evaluating computer vision models in agricultural disease detection and monitoring applications. The dataset contains 1,106 images across 8 classes: Brown Spot, Browon Spot, Leaf Scaled, Rice Blast, Rice Tungro, Rice Turgro, Shath Blight… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/Dhan-Shomadhan_rice_leaf_disease_classification.plum_leaf_disease_classification
Plum Leaf Disease Classification
A dataset for image classification of plum leaf disease. The dataset contains 2,400 images across 6 classes: Bacterial_Spot, Brown_Blight, Dry, Healthy, Powdery_Mildew, Sooty_Mold.Images per class:
Bacterial_Spot: 400
Brown_Blight: 400
Dry: 400
Healthy: 400
Powdery_Mildew: 400
Sooty_Mold: 400
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.
Citation
@article{bhowmik2024customised… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/plum_leaf_disease_classification.Rice-Disease-Classification-Dataset
🌾 Rice Disease Detection Dataset
Overview
The Rice Disease Detection Dataset is a curated collection of high-resolution images showcasing the health conditions of rice crops. It includes images across four distinct classes, enabling the development of machine learning models for detecting and diagnosing rice diseases effectively. This dataset is intended for agricultural researchers, machine learning enthusiasts, and AI practitioners working towards precision… See the full description on the dataset page: https://huggingface.co/datasets/LeafNet75/Rice-Disease-Classification-Dataset.tomato-leaf-disease-imageCOLD_onion_leaf_disease_classification
COLD Onion Leaf Disease Classification
A dataset for disease classification of onion leaves. The dataset contains raw and augmented versions.The raw dataset contains 815 images.Images per class:
Iris yellow virus: 281
Stemphylium leaf blight and collectrichum leaf blight: 90
healthy: 426
purple blotch: 18
The augmented dataset contains 4,502 images.Images per class:
Iris yellow virus: 1,272
Stemphylium leaf blight and collectrichum leaf blight: 1,217
healthy: 1,278
purple… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/COLD_onion_leaf_disease_classification.papaya_leaf_disease_classification_bd
Papaya Leaf Disease Classification Bd
A dataset for image classification of Papaya Leaf Disease Classification Bd. The dataset contains 11,074 images across 8 classes: Antracnose, Bacterial Spot, Healthy Leaf, Leaf Curl, Mealybug, Mite Disease, Mosaic, Ring Spot.Images per class:
Antracnose: 1,261
Bacterial Spot: 1,235
Healthy Leaf: 1,210
Leaf Curl: 1,982
Mealybug: 1,390
Mite Disease: 1,588
Mosaic: 1,118
Ring Spot: 1,290
This dataset is indexed on… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/papaya_leaf_disease_classification_bd.cotton_leaf_disease_classification
Cotton Leaf Disease Classification
A dataset for disease classification of cotton leaves. The dataset contains both the raw data and augmented version.The raw data contains 1373 images distributed between the classes as follows:
Alternaria Leaf Spot: 173 images
Bacterial Blight: 218 images
Fusarium Wilt: 337 images
Healthy Leaf: 333 images
Verticillium Wilt: 312 images
The augmented data contains 4963 images, again distributed as follows:
Alternaria_Leaf: 987 images… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/cotton_leaf_disease_classification.mandarin_leaf_variety_classification
Mandarin Leaf Variety Classification
A dataset for variety classification of Mandarin leaves. The dataset contains augmented and raw versions.
The augmented dataset contains 8,032 images.
Images per class:
China Mishti: 2,032
Darjeling: 2,000
Mendaring: 2,000
Nagpuri: 2,000
The raw dataset contains 1,917 images.
Images per class:
China Mishti: 511
Darjeling: 500
Mandaring: 540
Nagpuri: 366
This dataset is indexed on https://project-agml.github.io/ as part of the AgML python… See the full description on the dataset page: https://huggingface.co/datasets/Project-AgML/mandarin_leaf_variety_classification.