Flowers Image Classification Dataset
8.7K labeled images
Free download
8.7K+ labeled flowers images ready for AI and computer vision research. Delivered as an ImageFolder-style ZIP with train / val / test splits and class-labeled folders. Review the source license before use. Compatible with PyTorch, TensorFlow, Keras, and any classification pipeline.
Browse a selection of samples from the Flowers image dataset.
Categories in this dataset
Great masterwortBishop of llandaffArtichoke flowerBolero deep blueGazaniaSnapdragonColts footCanterbury bellsCanna lilyCarnationBlanket flowerPetuniaGlobe thistleWatercressButtercupTiger lilyCyclamenWindflowerBlackberry lilyHippeastrumFritillaryBougainvilleaBalloon flowerStemless gentianFire lilyGarden phloxKing proteaLove in the mistWallflowerTree mallowHibiscusPoinsettiaSword lilySunflowerLotusPincushion flowerGeraniumPink yellow dahliaSpear thistleOrange dahliaMallowRed gingerBlack eyed susanTrumpet creeperPeruvian lilyLenten roseThorn applePrince of wales feathersSpring crocusPelargoniumCalifornian poppyRuby lipped cattleyaGiant white arum lilyMarigoldDaffodilAzaleaCamelliaGlobe flowerJapanese anemoneCautleya spicataPassion flowerAnthuriumBarbeton daisyBee balmHard leaved pocket orchidToad lilyDaisyMexican petuniaCardoonClematisEnglish marigoldCape flowerYellow irisSweet williamTree poppyBearded irisSilverbushBromeliaBall mossDesert roseMorning gloryAlpine sea holly
Tags
Flowers labeled image dataset
Flowers photos
Flowers pictures
Flowers images
Flowers dataset
Flowers image dataset
Data sources
What you get
Flowers classification dataset, ready to train
Clean folder layout
`train` / `val` / `test` sub-folders per class plus a `meta.json` with label list, split counts, and ImageNet normalization constants — ready for `torchvision.datasets.ImageFolder`.
Your choices, your ZIP
Pick output size, color mode, train/val/test split, and 20 augmentations. The ZIP is built for your exact setup.
Research-friendly
BibTeX citation per dataset and a Colab starter notebook. No signup required to download.
Framework-agnostic
PyTorch, TensorFlow, Ultralytics — pick any. Standard ImageFolder layout works out of the box.
Ready to train?
Configure the split and augmentations, then grab the ZIP.