A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

July 27, 2017 · Entered Twilight · 🏛 arXiv.org

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: ILSVRC2015_clsloc_validation_ground_truth.txt, LICENSE, README.md, WRNs_imagenet.py, image2numpy_imagenet_train.py, image2numpy_imagenet_val.py, image_resizer_imagent.py, map_clsloc.txt, test.py, utils.py, val.txt

Authors Patryk Chrabaszcz, Ilya Loshchilov, Frank Hutter arXiv ID 1707.08819 Category cs.CV: Computer Vision Cross-listed cs.LG Citations 723 Venue arXiv.org Repository https://github.com/PatrykChrabaszcz/Imagenet32_Scripts ⭐ 155 Last Checked 1 month ago

Abstract

The original ImageNet dataset is a popular large-scale benchmark for training Deep Neural Networks. Since the cost of performing experiments (e.g, algorithm design, architecture search, and hyperparameter tuning) on the original dataset might be prohibitive, we propose to consider a downsampled version of ImageNet. In contrast to the CIFAR datasets and earlier downsampled versions of ImageNet, our proposed ImageNet32$\times$32 (and its variants ImageNet64$\times$64 and ImageNet16$\times$16) contains exactly the same number of classes and images as ImageNet, with the only difference that the images are downsampled to 32$\times$32 pixels per image (64$\times$64 and 16$\times$16 pixels for the variants, respectively). Experiments on these downsampled variants are dramatically faster than on the original ImageNet and the characteristics of the downsampled datasets with respect to optimal hyperparameters appear to remain similar. The proposed datasets and scripts to reproduce our results are available at http://image-net.org/download-images and https://github.com/PatrykChrabaszcz/Imagenet32_Scripts