ImageNet

class olympus.datasets.imagenet.ImagetNet(data_path, image_folder=<class 'torchvision.datasets.folder.ImageFolder'>, train_size=None, valid_size=None, test_size=None, input_shape=None, target_shape=None)

Bases: olympus.datasets.dataset.AllDataset

TThe ImageNet project is a large visual database designed for use in visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided. More on wikipedia.

The full specification can be found at here.

References

[1]	Olga Russakovsky*, Jia Deng*, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei.(* = equal contribution) ImageNet Large Scale Visual Recognition Challenge

Attributes:

classes: List[int]

Return the mapping between samples index and their class

input_shape: (3, 224, 224)

Size of a sample returned after transformation

target_shape: (1000,)

The classes are numbers from 0 to 999

train_size: 14000000

Size of the train dataset

valid_size:

Size of the validation dataset

test_size:

Size of the test dataset

Methods

categories()	Dataset tags so we can filter what we want depending on the task
transforms()

register_datapipe_as_function
register_function

static categories()

Dataset tags so we can filter what we want depending on the task

olympus.datasets.imagenet.default_transform()

olympus.datasets.imagenet.generate_jpeg_dataset(folder, shape=(3, 224, 224), num_class=1000, samples=192)

Generate a Fake JPEG Dataset for testing and benchmarking purposes

olympus.datasets.imagenet.make_benzina_data_loader(args, size)