Dataset Card for tiny-imagenet

  Dataset Summary

Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images, and 50 test images.

  Languages

The class labels in the dataset are in English.

  Dataset Structure





  Data Instances

{ 'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=64x64 at 0x1A800E8E190, 'label': 15 }… See the full description on the dataset page: https://huggingface.co/datasets/zh-plus/tiny-imagenet.

Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images and 50 test images.

The dataset used in the paper is CIFAR-10, CIFAR-100 and Tiny-Imagenet datasets.

Dataset Card for Tiny-ImageNet-C

  Dataset Details





  Dataset Description

In Tiny ImageNet-C, there are 75,109 corrupted images derived from the original Tiny ImageNet dataset. The images are affected by two different corruption types at five severity levels.

License: CC BY 4.0

  Dataset Sources

Homepage: https://github.com/hendrycks/robustness Paper: Hendrycks, D., & Dietterich, T. (2019). Benchmarking neural network robustness to common… See the full description on the dataset page: https://huggingface.co/datasets/randall-lab/tiny-imagenet-c.

Dataset

This dataset was created by Albert

Contents

iny Imagenet has 200 Classes, each class has 500 traininig images, 50 Validation Images and 50 test images. Label Classes and Bounding Boxes are provided. More details can be found at https://tiny-imagenet.herokuapp.com/",

This challenge is part of Stanford Class CS 231N

torch-uncertainty/tiny-imagenet-200 dataset hosted on Hugging Face and contributed by the HF Datasets community

TinyImageNet200 dataset created for Tiny-ImageNet Challenge at Stanford CS231N (http://cs231n.stanford.edu/reports/2015/pdfs/yle_project.pdf)

The dataset used in the paper is CIFAR-10, Tiny ImageNet, and ImageNet.

Dataset

This dataset was created by zhanghongyu

Contents

Predictions generated by an ensemble of 4 ResNet 34 Deep Neural Networks Trained on TinyImagenet, as used in repository https://anonymous.4open.science/r/ensemble_attention-7616/README.md. Ensembles are trained to encourage/discourage predictive diversity. Each timestamped folder contains individual training runs, with the labels and probabilistic predictions of the ensemble on 1) the training set (train_labels.npy, train_preds.npy) and 2) the test set (ind_labels.npy, ind_preds.npy) for tinyimagenet. The file (tinyimagenet/resnet34/version_0/hparams.yaml) contains specific hyperparameters used on a particular training run. Figures visualizing training results can be generated by:
1.unzipping the four folders in to the directory `ensemble_attention/scripts/outputs/`
2. running the script `ensemble_attention/scripts/vis_scripts/all_weights_resnet34_tinyimagenet.py`.

Dataset

This dataset was created by Arghya Dutta

Contents

Dataset

This dataset was created by Akash Sharma

Contents

Upload of the corrupted version of Tiny ImageNet (also known as ImageNet-200) with fixed frost-corrupted samples (see https://github.com/hendrycks/robustness/issues/60). This version can be downloaded on a server (for instance using TorchUncertainty) and is safer than the original mirror on berkeley connect (that may soon be deleted).

Original work by Dan Hendrycks & Thomas Dietterich under the Apache-2.0 license. If you consider this dataset useful, please cite:

@article{hendrycks2019robustness,
 title={Benchmarking Neural Network Robustness to Common Corruptions and Perturbations},
 author={Dan Hendrycks and Thomas Dietterich},
 journal={Proceedings of the International Conference on Learning Representations},
 year={2019}
}

Dataset

This dataset was created by BANUTEJA008

Released under MIT

Contents

Classification accuracy against PGD-10 attacks on different datasets.

Dataset

This dataset was created by kikoOne

Released under CC0: Public Domain

Contents

goddawg/tiny-imagenet-2k dataset hosted on Hugging Face and contributed by the HF Datasets community

Tiny-ImageNet-R, is a down-sampled subset of ImageNet-R(enditions) imagenet-r. It contains roughly 12,000 samples categorized in 64 classes (a subset of Tiny-ImageNet classes), spread across multiple visual domains such as art, cartoons, sculptures, origami, graffiti, and embroidery.

CIFAR-10, CIFAR-100, Tiny ImageNet, SVHN, iSUN, LSUN