Tiny ImageNet

class olympus.datasets.tinyimagenet.TinyImageNet(data_path)

Bases: olympus.datasets.dataset.AllDataset

Tiny Imagenet has 200 classes. Each class has 500 training images, 50 validation images, and 50 test images. We have released the training and validation sets with images and annotations. We provide both class labels and bounding boxes as annotations; however, you are asked only to predict the class label of each image without localizing the objects. The test set is released without labels. More at tiny-imagenet.

References

[1]	Jiayu Wu, Qixiang Zhang, Guoxi Xu. “Tiny ImageNet Challenge”, 2017

Attributes:

classes: List[int]

Return the mapping between samples index and their class

input_shape: (3, 64, 64)

Size of a sample stored in this dataset

target_shape: (200,)

The dataset is composed of 200 classes

train_size: 90000

Size of the train dataset

valid_size: 10000

Size of the validation dataset

test_size: 10000

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.tinyimagenet.all_hdf5_exists(data_path)

olympus.datasets.tinyimagenet.build_dataset(data_path, timeout=600)

olympus.datasets.tinyimagenet.clean(data_path)

olympus.datasets.tinyimagenet.create_hdf5(data_path)

olympus.datasets.tinyimagenet.create_hdf5_file(dirpath, file_path, n, dataloader)

olympus.datasets.tinyimagenet.create_hdf5_train(dirpath, file_path)

olympus.datasets.tinyimagenet.create_hdf5_val(dirpath, file_path)

olympus.datasets.tinyimagenet.create_train_loader(dirpath)

olympus.datasets.tinyimagenet.create_val_loader(dirpath)

olympus.datasets.tinyimagenet.download(data_path)

olympus.datasets.tinyimagenet.get_dirpath(data_path)

olympus.datasets.tinyimagenet.get_zipfile_path(data_path)

olympus.datasets.tinyimagenet.unzip(data_path)