The Oxford Flower Dataset is a 102 category dataset, consisting of 102 flower categories. The flowers chosen to be flower commonly occuring in the United Kingdom. Each class consists of between 40 and 258 images. The details of the categories and the number of images for each class can be found on this category statistics page.
oxford_flowers102_dataset(
root,
split = "train",
target_type = c("categories"),
download = FALSE,
...,
transform = NULL,
target_transform = NULL
)path to the data location
train, test or valid
Currently only 'categories' is supported.
wether to download or not
Currently unused.
A function/transform that takes in an PIL image and returns
a transformed version. E.g, transform_random_crop().
A function/transform that takes in the target and transforms it.
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 visualized using isomap with shape and colour features.
You can find more info in the dataset webpage.
The official splits leaves far too many images in the test set. Depending on your work you might want to create different train/valid/test splits.