Context

This dataset contains 3122 images (512x512) of 215 different mushrooms (at least 4 images per class). mushrooms.txt contains names of all the mushrooms in the dataset.

Legal notice

The dataset was created with the images, that were obtained from WildFoodUK. I'm not responsible for the use of the dataset

Inspiration

The original idea was to create an android application with mushrooms detection capabilities, but all that was done is this dataset.

This dataset contains 2,820 high-quality images of various mushroom species, meticulously categorized into edible and poisonous classes. The dataset provides a diverse collection of 25 edible mushroom species and 22 poisonous mushroom species, capturing a wide range of visual features such as color, shape, texture, and size variations.

To ensure an optimal data distribution for machine learning and deep learning applications, the dataset has been strategically split into three subsets:

Training Set (80%) – Comprising 2,256 images, this subset serves as the primary source for model learning, offering a comprehensive range of mushroom species. Validation Set (10%) – Consisting of 282 images, this subset is used for hyperparameter tuning and performance evaluation to mitigate overfitting. Test Set (10%) – Including 282 images, this subset is reserved for final model evaluation to assess its generalization capability on unseen data. The dataset is structured into two main categories:

Edible Mushrooms (25 species) Poisonous Mushrooms (22 species) Unlike raw datasets that maintain species-specific subdirectories, this dataset organizes images directly under their respective labels (edible/ and poisonous/). This format simplifies its integration with deep learning frameworks such as TensorFlow, PyTorch, and Keras, making it well-suited for image classification tasks, mushroom species recognition, and toxicity prediction.

This dataset can be applied to various domains, including computer vision research, mycology studies, AI-driven foraging assistance, and food safety analysis.

Collection Credit: https://www.kaggle.com/datasets/yoonjunggyu/25-edible-mushroom-and-25-poisonous-mushroom

Context

We created this dataset as part of our school's research project. As we didn't find something similar when we started, we decided to publish it here so that future research with mushrooms and AI can benefit from it.

Content

The dataset is separated in 2 classes , mushroom sporocarps and not mushroom sporocarps. Each class has 2 subclasses, edible and non-edible(includes medicinal, unpalatable and hallucinogenic fungi).

Acknowledgements

A HUGE thanks to my colleagues: Gabriel and Bianca. Without you guys this dataset wouldn't be possible

Inspiration

(◕ᴗ◕✿) Be cool!

This dataset is used to classify 9 kinds of mushroom.
If you like this dataset and find it useful, please give a thumbs up 👍👍👍👍
💥💥💥💥💥
Pay attention that there are some truncated images in this dataset(maybe only one, I'm not sure), so you are not recommended to use function like ImageFolder to load the whole dataset.
Otherwise, you will get OS Error, which I have shown you in my notebook. It's better to rewrite Dataset class.

Data exported from inaturalist with

place: Russia Federation

tag: Fungi Including Lichens

Categories

1. Amanita citrina
2. Amanita muscaria
3. Amanita pantherina
4. Amanita rubescens
5. Apioperdon pyriforme
6. Armillaria borealis
7. Artomyces pyxidatus
8. Bjerkandera adusta
9. Boletus edulis
10. Boletus reticulatus
11. Calocera viscosa
12. Calycina citrina
13. Cantharellus cibarius
14. Cerioporus squamosus
15. Cetraria islandica
16. Chlorociboria aeruginascens
17. Chondrostereum purpureum
18. Cladonia fimbriata
19. Cladonia rangiferina
20. Cladonia stellaris
21. Clitocybe nebularis
22. Coltricia perennis
23. Coprinellus disseminatus
24. Coprinellus micaceus
25. Coprinopsis atramentaria
26. Coprinus comatus
27. Crucibulum laeve
28. Daedaleopsis confragosa
29. Daedaleopsis tricolor
30. Evernia mesomorpha
31. Evernia prunastri
32. Flammulina velutipes
33. Fomes fomentarius
34. Fomitopsis betulina
35. Fomitopsis pinicola
36. Ganoderma applanatum
37. Graphis scripta
38. Gyromitra esculenta
39. Gyromitra gigas
40. Gyromitra infula
41. Hericium coralloides
42. Hygrophoropsis aurantiaca
43. Hypholoma fasciculare
44. Hypholoma lateritium
45. Hypogymnia physodes
46. Imleria badia
47. Inonotus obliquus
48. Kuehneromyces mutabilis
49. Lactarius deliciosus
50. Lactarius torminosus
51. Lactarius turpis
52. Laetiporus sulphureus
53. Leccinum albostipitatum
54. Leccinum aurantiacum
55. Leccinum scabrum
56. Leccinum versipelle
57. Lepista nuda
58. Lobaria pulmonaria
59. Lycoperdon perlatum
60. Macrolepiota procera
61. Merulius tremellosus
62. Mutinus ravenelii
63. Nectria cinnabarina
64. Panellus stipticus
65. Parmelia sulcata
66. Paxillus involutus
67. Peltigera aphthosa
68. Peltigera praetextata
69. Phaeophyscia orbicularis
70. Phallus impudicus
71. Phellinus igniarius
72. Phellinus tremulae
73. Phlebia radiata
74. Pholiota aurivella
75. Pholiota squarrosa
76. Physcia adscendens
77. Platismatia glauca
78. Pleurotus ostreatus
79. Pleurotus pulmonarius
80. Pseudevernia furfuracea
81. Rhytisma acerinum
82. Sarcomyxa serotina
83. Sarcoscypha austriaca
84. Sarcosoma globosum
85. Schizophyllum commune
86. Stereum hirsutum
87. Stropharia aeruginosa
88. Suillus granulatus
89. Suillus grevillei
90. Suillus luteus
91. Trametes hirsuta
92. Trametes ochracea
93. Trametes versicolor
94. Tremella mesenterica
95. Trichaptum biforme
96. Tricholomopsis rutilans
97. Urnula craterium
98. Verpa bohemica
99. Vulpicida pinastri
100. Xanthoria parietina

Description:

This dataset comprises images of 12 distinct species of mushrooms, collected from various sources, primarily sourced from Mushroom World. The species included are Agaricus, Amanita, Boletus, Cortinarius, Entoloma, Exidia, Hygrocybe, Inocybe, Lactarius, Pluteus, Russula, and Suillus, representing a diverse array of fungal taxa.

Dataset Contents: - Images of mushrooms from each species, captured under varying conditions. - Ground truth labels are provided for each image, indicating the species of mushroom depicted. - Images have been processed using GrabCut segmentation to isolate the mushrooms from their backgrounds, facilitating easier analysis and classification.

Applications:

• Classification and identification of mushroom species using machine learning and computer vision techniques.
• Research into fungal taxonomy and biodiversity.
• Educational purposes, including mushroom identification guides and apps.

Usage Notes:

• This dataset is suitable for training and testing machine learning models for mushroom species classification.
• Researchers and enthusiasts interested in mycology can utilize this dataset for various analyses and studies.
• Proper citation of the original data sources, including Mushroom World, is encouraged when using this dataset in publications or projects.

Acknowledgments:

• The source of the images is primarily from Mushroom World, and credit is given to them for providing the foundational data for this dataset.
• The GrabCut segmentation technique used to process the images was applied to isolate the mushrooms from their backgrounds, enhancing the usability of the dataset for classification tasks.

Note to Users: - Please ensure compliance with any licensing or usage restrictions associated with the original images obtained from Mushroom World. - Feedback and contributions to enhance the dataset are welcome and appreciated.

Published Paper similar to this dataset: https://www.hindawi.com/journals/jfq/2022/1173102/

Dataset

This dataset was created by Irakli DD

Released under MIT

Contents

The dataset includes 8857 images. Mushroom are annotated in COCO format.

The following pre-processing was applied to each image: * Auto-orientation of pixel data (with EXIF-orientation stripping) * Resize to 640x640 (Stretch)

The following augmentation was applied to create 3 versions of each source image: * 50% probability of horizontal flip * 50% probability of vertical flip

The structure:

dataset-directory/
├─ README.dataset.txt
├─ README.roboflow.txt
├─ train
│ ├─ train-image-1.jpg
│ ├─ train-image-1.jpg
│ ├─ ...
│ └─ _annotations.coco.json
├─ test
│ ├─ test-image-1.jpg
│ ├─ test-image-1.jpg
│ ├─ ...
│ └─ _annotations.coco.json
└─ valid
  ├─ valid-image-1.jpg
  ├─ valid-image-1.jpg
  ├─ ...
  └─ _annotations.coco.json

To convert the format to YOLO annotations, go to roboflow.

Mushrooms of the Northeast United States

Mushrooms of the Northeast United States is a collection of images of the fruiting bodies (mushrooms) of various species of fungus common to the Northeast and New England area of North America.

Technical detalils The images are in unedited JPG format and appear as scraped from the web. The images are intended for use in the training of machine learning models for image classification. They have been subdivided into directories according to their common species name, and the directory labels can be used for labeling ground truth during training of machine learning models.

Versioning This initial version of the image collection have not been hand-labeled, but represent only the keyword search under which they were initially collected from the web. Future versions will be hand culled and mislabeled or otherwise inappropriate images will be removed to improve data quality. Additionally it is hoped that the collection will be expanded to include a larger number of species.
The current version, v0.2, includes images of chicken of the woods. destroying angel, fly agaric, honey mushroom, leafy brain, lobster mushroom, oyster mushroom and witch's butter. The collection currently contains approximately 440 images over 8 categories, and totals 230.4 MB.

Mushroom image dataset for classification, based on mushrooms in Bosnia. Sources: mushroom species pulled from "Gljive: šumsko bogatstvo Bosne i Hercegovine" book by Hajrudin Rudi Hasanbegović. Mushroom images for dataset based on https://www.kaggle.com/datasets/derekkunowilliams/mushrooms and https://github.com/bechtle/mushroomobser-dataset

This dataset contains 27,436 images of mushrooms, categorized into 94 species. The distribution among species varies, with the largest species containing 581 images and the smallest having 212, while the average size is 291 images per species. The mushrooms are classified into three categories: edible, non-edible, and toxic.

Edible mushrooms include: 1. Volvopluteus gloiocephalus 2. Agaricus augustus 3. Amanita amerirubescens 4. Amanita calyptrodermsa 5. Armillaria mellea (may cause allergic reactions or stomach upset in some individuals) 6. Armillaria tabescens 7. Artomyces pyxidatus 8. Bolbitius titubans 9. Boletus pallidus 10. Boletus rex-veris 11. Cantharellus californicus 12. Cantharellus cinnabarinus 13. Cerioporus squamosus (edible when young) 14. Chlorophyllum brunneum 15. Clitocybe nuda 16. Coprinellus micaceus 17. Coprinus comatus (used in medicine and considered delicious) 18. Flammulina velutipes 19. Entoloma abortivum 20. Ganoderma applanatum (inedible when raw, cooked it's edible) 21. Ganoderma oregonense 22. Grifola frondosa (may cause mild gastrointestinal distress) 23. Hericium coralloides 24. Hericium erinaceus 25. Hypomyces lactifluorum 26. Ischnoderma resinosum 27. Laccaria ochropurpurea 28. Lacrymaria lacrymabunda 29. Lactarius indigo 30. Laetiporus sulphureus 31. Lycoperdon perlatum 32. Lycoperdon pyriforme 33. Mycena haematopus 34. Pleurotus ostreatus 35. Pleurotus pulmonarius 36. Pluteus cervinus 37. Psathyrella candolleana 38. Pseudohydnum gelatinosum 39. Psilocybe cyanescens 40. Psilocybe muliercula 41. Psilocybe pelliculosa 42. Psilocybe zapotecorum 43. Retiboletus ornatipes 44. Sarcomyxa serotina 45. Stropharia ambigua 46. Stropharia rugosoannulata 47. Suillus americanus 48. Suillus luteus 49. Suillus spraguei 50. Tricholoma murrillianum

Non-edible mushrooms include:

1. Tylopilus rubrobrunneus (bitter taste)
2. Tylopilus felleus (bitter taste)
3. Coprinopsis lagopus
4. Crucibulum laeve
5. Cryptoporus volvatus
6. Fomitopsis mounceae (toxic but potentially medicinal)
7. Ganoderma curtisii
8. Ganoderma tsugae
9. Gliophorus psittacinus (mildly poisonous)
10. Gloeophyllum sepiarium
11. Gymnopilus luteofolius (bitter taste)
12. Laricifomes officinalis (bitter taste, used in medicine)
13. Leucoagaricus americanus (edible but should be avoided due to confusion with toxic species)
14. Leucoagaricus leucothites (generally edible but slightly poisonous)
15. Lycogala epidendrum (not toxic but may cause gastrointestinal discomfort)
16. Mycena leaiana (edibility unknown)
17. Panaeolus foenisecii
18. Panellus stipticus (bitter taste)
19. Phaeolus schweinitzii (bitter taste)
20. Phyllotopsis nidulans
21. Psilocybe caerulescens (edibility unknown)
22. Psilocybe cubensis (information not available)
23. Psilocybe neoxalapensis (no information available)
24. Schizophyllum commune
25. Stereum ostrea
26. Tapinella atrotomentosa
27. Trametes versicolor (not directly edible)
28. Trametes gibbosa
29. Trametes betulina
30. Trichaptum biforme
31. Tricholomopsis rutilans (bitter taste)
32. Tubaria furfuracea

Toxic mushrooms include: 1. Agaricus xanthodermus 2. Amanita augusta 3. Amanita brunnescens 4. Amanita flavoconia 5. Amanita muscaria 6. Amanita persicina 7. Amanita velosa 8. Chlorophyllum molybdites 9. Daedaleopsis confragosa 10. Galerina marginata 11. Hygrophoropsis aurantiaca 12. Hypholoma fasciculare 13. Hypholoma lateritium 14. Leratiomyces ceres 15. Omphalotus illudens 16. Omphalotus olivascens 17. Panaeolus cinctulus 18. Panaeolus papilionaceus 19. Phlebia tremellosa 20. Psilocybe allenii 21. Psilocybe azurescens 22. Psilocybe aztecorum 23. Psilocybe ovoideocystidiata

This dataset was created as part of my bachelor's thesis. Images collected from Mushroom Observer and FGVCx. The dataset contains train and test subsets. Dataset has been augmented. Images are sized 299x299 pixels. There are 8 classes of mushrooms.

Acknowledgements:

• 2018 FGVCx Fungi Classification Challenge (https://github.com/visipedia/fgvcx_fungi_comp)
• Mushroom Observer (https://mushroomobserver.org/)

Content

There is 9 folders of images of most common Northern European mushrooms genuses inside of this dataset. Each folder consist of from 300 to 1500 selected images of mushrooms genuses. Labels are the folder's names.

Acknowledgements

Special thanks to mycologist's society of Northern Europe, who provided the sources of most common mushrooms in this area and checked data and labels.

Inspiration

Your data will be in front of the world's largest data science community. What questions do you want to see answered?

The oyster mushroom data set was annotated for my master thesis for finding the matured oyster mushrooms from not matured and overdue mushrooms , the images are annotated for YOLO version 8 CNN based algorithm. The bounding box coordinates along with the class labels with the same image names used for training. The Thesis can be found out in my GitHub page https://github.com/MSAthira

This dataset contains images of different mushroom species, divided into over 100 classes, each corresponding to a specific species. The images show mushrooms in various growth stages and conditions, making the dataset ideal for fine-grained classification tasks. The data is organized into three CSV files: train.csv for training, val.csv for validation and optimization of the model during training, and test.csv for the final performance evaluation. Each CSV file includes image paths and corresponding species labels, making it easy to use for machine learning models.

Contains images downloaded from google of different classes of mushrooms listed on Wikipedia. These classes are deadly, poisonous, conditionally edible, and edible. Additionally, the genus and species is listed for each species in the format, Genus_species. This dataset could be used to classify by species, genus, or if edible. Possible inaccuracies in this dataset may lead to misclassification of edible and inedible species. Please ensure that the dataset is not used to determine the safety of consuming mushroom species.

Overview

The Plant Pathogen Classification Dataset comprises a diverse collection of images depicting various plant diseases caused by pathogens such as fungi, bacteria, viruses, pests and seperate class of healthy leaves. Each image in the dataset is storedwith the corresponding disease type, providing valuable information for researchers and practitioners in plant pathology and agriculture.

Dataset Composition

The dataset contains high-resolution images captured under different lighting conditions and perspectives, showcasing symptoms of plant diseases across multiple plant species.

Key Features

Disease Diversity

Covers a wide range of plant species and diseases, including common pathogens affecting crops, ornamental plants, and trees.

Image Variability

Includes images captured under varying environmental conditions and growth stages, ensuring robustness and generalization of classification models.

Potential Applications

Disease Detection

Enables the development of machine learning models for automated detection and classification of plant diseases, aiding in early diagnosis and mitigation strategies.

Crop Management

Supports precision agriculture initiatives by providing tools for monitoring and managing disease outbreaks, optimizing crop yield and quality.

Research and Education

Serves as a valuable resource for researchers, educators, and practitioners in plant pathology, fostering innovation and knowledge dissemination in the field.

DeFungi is a dataset for direct mycological examination of microscopic fungi images. The images are from superficial fungal infections caused by yeasts, moulds, or dermatophyte fungi. The images have been manually labelled into five classes and curated with a subject matter expert assistance. The images have been cropped with automated algorithms to produce the final dataset.

Introductory Paper

P456 Defungi: direct mycological examination of microscopic fungi images

By C. Sopo, Farshid Hajati, S. Gheisari. 2021 Published in Medical Mycology

Ces datasets sont utilisés pour le cours de Centrale Lille sur le Machine Learning de Pascal Yim (Image générée avec ideogram.ai)

Régression

"datareg_xxx_yyy.csv"

Exemples simples pour la regression Par exemple "datareg_cos_300.csv" est un ensemble de 300 points suivant un cosinus bruité avec deux colonnes 'x' et 'y'

"housing.csv"

Estimation de la valeur moyenne des maisons (MEDV) par quartier en fonction de différentes données : - RM : nombre de chambres - LSTAT : mesure du taux de pauvreté - PTRATIO : mesure du taux d'encadrement par élève dans les écoles

Version simplifiée du dataset original UCI

Source : https://www.kaggle.com/datasets/schirmerchad/bostonhoustingmlnd

"kc_house_data.csv"

Prédiction de prix de maisons aux alentours de Seattle (district de King County)

Source : https://www.kaggle.com/datasets/harlfoxem/housesalesprediction

"house_prices.csv"

Prédiction de prix de maisons - Compétition Kaggle

Source : https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques/data?select=train.csv

Classification

"geyser.csv"

Le geyser « Old Faithful » est un geyser en cône du parc de Yellowstone aux États-Unis

On a mesuré : - duration : la durée de l’éruption - waiting : l’intervalle de temps depuis la dernière éruption - kind : une étiquette 'short' ou 'long' du type d’éruption

"iris.csv"

Dataset pour classifier les espèces d'Iris

https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQM3aH4Q3AplfE1MR3ROAp9Ok35fafmNT59ddXkdEvNdMkT8X6E">

On a les informations suivantes : - sepal_length : longueur du sépale (en cm) - sepal_width : largeur du sépale - length,petal : longueur du pétale - petal_width : largeur du pétale - species : 3 espèces d'iris : 'setosa', 'versicolor' ou 'virginica'

Source : UCI (http://archive.ics.uci.edu/)

"iris_basic.csv"

Une version simplifiée du dataset des iris, avec seulement les mesures de pétales et 2 espèces : versicolor (0) et virginica (1)

"heart.csv"

Prédiction de malaise cardiaque (output) en fonction de différents paramètres comme l'âge, le taux de cholesterol, ...

Source : https://www.kaggle.com/rashikrahmanpritom/heart-attack-analysis-prediction-dataset

"cancer.csv"

On veut prédire si une tumeur est maline ou non, en fonction de mesures sur une biopsie de la tumeur

Source : https://www.kaggle.com/uciml/breast-cancer-wisconsin-data

"penguins.csv"

Dataset comparable à celui des Iris. On veut prédire l'espèce de manchots

• species : Adelie, Chinstrap, Gentoo
• island : Biscoe, Dream, Torgersen
• bill_length_mm : longueur du bec
• bill_depth_mm : épaisseur du bec
  • flipper_length_mm : longueur de la nageoire
• body_mass_g : poids
• sex : “male” ou “female”

Source : https://www.kaggle.com/ashkhagan/palmer-penguins-datasetalternative-iris-dataset

"stars.csv"

Classification d'étoiles

Source : https://www.kaggle.com/datasets/deepu1109/star-dataset

"mushrooms.csv"

Prédire si un champignon est comestible ou non

Source : https://www.kaggle.com/uciml/mushroom-classification

"titanic.csv"

Dataset très classique sur les survivants du Titanic

Source : https://www.kaggle.com/c/titanic

"diabetes.csv"

Dataset "PIMA Indian diabete"

Prédiction du diabète pour une population de femmes de la tribu Pima

Source : https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database

"churn-small.csv"

On veut prédire le départ de clients pour la concurrence de clients Orange telecom (problème de ‘churn’ ou ‘attrition’)

Version "churn-big.csv" avec plus de données

Source : https://www.kaggle.com/datasets/mnassrib/telecom-churn-datasets

"stroke.csv"

Prédiction d'attaque cérébrale

Source : https://www.kaggle.com/datasets/shashwatwork/cerebral-stroke-predictionimbalaced-dataset

"predictive_maintenance.csv"

Prédiction de pannes (UCI)

Source : https://www.kaggle.com/datasets/shivamb/machine-predictive-maintenance-classification/code

● Data provided by Kaggle and Mushroom World ● Total images data taken was 9533 and are in RGB. ● Mushrooms with each common genus name contain (edible, non-edible, and poisonous types). ● Genus of mushroom can be identified based on the following attributes: ● Color and structures of cap (likes egg-shaped, expanding cap, umbrella shape, ball shape) ● Thickness, length of the stem, and habitat ● Count for the number of images taken for each class from the different sources are given below: