Oxford Flowers 102

Other names: tfds:oxford_flowers102

Visit the original source

Overview

The Oxford Flowers 102 dataset is a consistent of 102 flower categories commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images.

Description (from the source)

The Oxford Flowers 102 dataset is a consistent of 102 flower categories commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images. The images have large scale, pose and light variations. In addition, there are categories that have large variations within the category and several very similar categories. The dataset is divided into a training set, a validation set and a test set. The training set and validation set each consist of 10 images per class (totalling 1020 images each). The test set consists of the remaining 6149 images (minimum 20 per class). Note: The dataset by default comes with a test size larger than the train size. For more info see this issue.

Domain
Computer Vision
Data type
Images
Tasks
Fine-grained Image Classification, Image Classification, Image Generation
Subfields
Image classification, Image generation
Languages
Not available
Tags
Not available

Statistics and structure

Number of samples
8,189
Number of classes
102
Number of features
Not available
Number of subjects / cases
Not available
Number of images
Not available
Number of files
Not available
Size
328.9 MB
Formats
Not available
Missing values
Not available

Samples note: Sum of the splits: test, train, validation. Size note: Size of the source files when downloaded (downloadSize).

Licence and access

Licence
Unknown — no explicit licence is stated in the sources relied on
Licence documentation
Unknown
Commercial use
Unknown
Redistribution
Unknown
Attribution required
Unknown
Access method
Visit the source
Access restrictions
Not available
Terms of use
Not available

No explicit licence was found in the sources used; do not assume any permission before reviewing the original source.

Always review the original publisher's terms before use; the explorer grants no licence.

Source and download

Platform
TensorFlow Datasets catalog
Publisher / source
TensorFlow Datasets (TFDS)
Identifier at the source
tfds:oxford_flowers102
DOI
Not available
Metadata source
tfds
Metadata last updated
2026-11-14

The explorer does not host data files; all links point to the original publisher.

Related papers

  1. Paper that introduced the dataset
    Nilsback, M-E., Zisserman, A. (2008). Automated Flower Classification over a Large Number of Classes. Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing.
    Listed for this dataset in the source catalogue · Evidence

Cite the dataset

Built from recorded fields only; missing fields are omitted, not guessed. It is also good practice to cite the paper that introduced the dataset, if there is one.

APA 7
Oxford Flowers 102 [Data set]. (2008). TensorFlow Datasets (TFDS). https://www.robots.ox.ac.uk/~vgg/data/flowers/102/
IEEE
[1] "Oxford Flowers 102," TensorFlow Datasets (TFDS), 2008. [Online]. Available: https://www.robots.ox.ac.uk/~vgg/data/flowers/102/
BibTeX
@misc{oxfordflowers1022008,
  title = {{Oxford Flowers 102}},
  year = {2008},
  publisher = {TensorFlow Datasets (TFDS)},
  url = {https://www.robots.ox.ac.uk/~vgg/data/flowers/102/},
  howpublished = {\url{https://www.robots.ox.ac.uk/~vgg/data/flowers/102/}},
  note = {Dataset. Accessed: 2026-11-22}
}

Verification

Verification status
Partially verified
Last link check
Not checked yet
Source verification date
Not available
Verification method
Metadata imported from the official TensorFlow Datasets catalog (dataset_info.json on storage.googleapis.com and the tensorflow-datasets 4.9.10 package).
Notes
Counts and sizes come from the TFDS-prepared version 2.1.1. Licence not stated in TFDS metadata unless shown; check the original source. Original URL not yet checked for availability.
Source and check date of each field
FieldSourceDate
original_urlTFDS dataset_info.json (location.urls)2026-11-14
descriptionTFDS README.md / dataset_info.description2026-11-14
number_of_samplesTFDS dataset_info.json splits[].numExamples (version 2.1.1)2026-11-14
number_of_classesTFDS label.labels.txt (number of label names)2026-11-14
dataset_sizeTFDS dataset_info.json downloadSize2026-11-14

Similar datasets

Computer Vision Partially verified

Stanford Dogs

The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet…

Samples
20,580
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog
Computer Vision Partially verified

STL-10

The STL-10 dataset is an image recognition dataset for developing unsupervised feature learning, deep learning, self-taught learning algorithms. It is inspired by the CIFAR-10 dataset but…

Samples
113,000
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog
Computer Vision Partially verified

CelebA

CelebFaces Attributes Dataset (CelebA) is a large-scale face attributes dataset with more than 200K celebrity images, each with 40 attribute annotations. The images in this dataset…

Samples
202,599
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog
Computer Vision Partially verified

Caltech-101

Caltech-101 consists of pictures of objects belonging to 101 classes, plus one `background clutter` class. Each image is labelled with a single object.

Samples
9,144
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog
Computer Vision Partially verified

ImageNet (ILSVRC 2012)

ILSVRC 2012, commonly known as 'ImageNet' is an image dataset organized according to the WordNet hierarchy. Each meaningful concept in WordNet, possibly described by multiple words…

Samples
1,431,167
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog
Computer Vision Partially verified

Oxford-IIIT Pet

The Oxford-IIIT pet dataset is a 37 category pet image dataset with roughly 200 images for each class. The images have large variations in scale, pose…

Samples
7,349
Type
Images
Licence
Unknown
Source
TensorFlow Datasets catalog